IA Scholar Query: Upper and Lower Amortized Cost Bounds of Programs Expressed as Cost Relations.
https://scholar.archive.org/
Internet Archive Scholar query results feedeninfo@archive.orgWed, 28 Sep 2022 00:00:00 GMTfatcat-scholarhttps://scholar.archive.org/help1440Quantum Subroutine Composition
https://scholar.archive.org/work/22jzvb2zefa4dpm2xuxijdqnxu
An important tool in algorithm design is the ability to build algorithms from other algorithms that run as subroutines. In the case of quantum algorithms, a subroutine may be called on a superposition of different inputs, which complicates things. For example, a classical algorithm that calls a subroutine Q times, where the average probability of querying the subroutine on input i is p_i, and the cost of the subroutine on input i is T_i, incurs expected cost Q∑_i p_i E[T_i] from all subroutine queries. While this statement is obvious for classical algorithms, for quantum algorithms, it is much less so, since naively, if we run a quantum subroutine on a superposition of inputs, we need to wait for all branches of the superposition to terminate before we can apply the next operation. We nonetheless show an analogous quantum statement (*): If q_i is the average query weight on i over all queries, the cost from all quantum subroutine queries is Q∑_i q_i E[T_i]. Here the query weight on i for a particular query is the probability of measuring i in the input register if we were to measure right before the query. We prove this result using the technique of multidimensional quantum walks, recently introduced in arXiv:2208.13492. We present a more general version of their quantum walk edge composition result, which yields variable-time quantum walks, generalizing variable-time quantum search, by, for example, replacing the update cost with √(∑_u,vπ_u P_u,v E[T_u,v^2]), where T_u,v is the cost to move from vertex u to vertex v. The same technique that allows us to compose quantum subroutines in quantum walks can also be used to compose in any quantum algorithm, which is how we prove (*).Stacey Jefferywork_22jzvb2zefa4dpm2xuxijdqnxuWed, 28 Sep 2022 00:00:00 GMTOptimization of Annealed Importance Sampling Hyperparameters
https://scholar.archive.org/work/3ffd2mewuvdqzata4vedmyx35e
Annealed Importance Sampling (AIS) is a popular algorithm used to estimates the intractable marginal likelihood of deep generative models. Although AIS is guaranteed to provide unbiased estimate for any set of hyperparameters, the common implementations rely on simple heuristics such as the geometric average bridging distributions between initial and the target distribution which affect the estimation performance when the computation budget is limited. Optimization of fully parametric AIS remains challenging due to the use of Metropolis-Hasting (MH) correction steps in Markov transitions. We present a parameteric AIS process with flexible intermediary distributions and optimize the bridging distributions to use fewer number of steps for sampling. A reparameterization method that allows us to optimize the distribution sequence and the parameters of Markov transitions is used which is applicable to a large class of Markov Kernels with MH correction. We assess the performance of our optimized AIS for marginal likelihood estimation of deep generative models and compare it to other estimators.Shirin Goshtasbpour, Fernando Perez-Cruzwork_3ffd2mewuvdqzata4vedmyx35eTue, 27 Sep 2022 00:00:00 GMTAn adaptive wavelet method for nonlinear partial differential equations with applications to dynamic damage modeling
https://scholar.archive.org/work/dfepnpsbc5fm5p73p2nwd5ntim
Multiscale and multiphysics problems need novel numerical methods in order for them to be solved correctly and predictively. To that end, we develop a wavelet based technique to solve a coupled system of nonlinear partial differential equations (PDEs) while resolving features on a wide range of spatial and temporal scales. The algorithm exploits the multiresolution nature of wavelet basis functions to solve initial-boundary value problems on finite domains with a sparse multiresolution spatial discretization. By leveraging wavelet theory and embedding a predictor-corrector procedure within the time advancement loop, we dynamically adapt the computational grid and maintain accuracy of the solutions of the PDEs as they evolve. Consequently, our method provides high fidelity simulations with significant data compression. We present verification of the algorithm and demonstrate its capabilities by modeling high-strain rate damage nucleation and propagation in nonlinear solids using a novel Eulerian-Lagrangian continuum framework.Cale Harnish, Luke Dalessandro, Karel Matous, Daniel Livescuwork_dfepnpsbc5fm5p73p2nwd5ntimMon, 26 Sep 2022 00:00:00 GMTMASADA: From Microlensing Planet Mass-Ratio Function to Planet Mass Function
https://scholar.archive.org/work/cvoaqm4zobgwpbfyz3uw6h2yqi
Using current technology, gravitational microlensing is the only method that can measure planet masses over the full parameter space of planet and stellar-host masses and at a broad range of planet-host separations. I present a comprehensive program to transform the ∼ 150 planet/host mass ratio measurements from the first 6 full seasons of the KMTNet survey into planet mass measurements via late-time adaptive optics (AO) imaging on 30m-class telescopes. This program will enable measurements of the overall planet mass function, the planet frequency as a function of Galactic environment and the planet mass functions within different environments. I analyze a broad range of discrete and continuous degeneracies as well as various false positives and false negatives, and I present a variety of methods to resolve these. I analyze the propagation from measurement uncertainties to mass and distance errors and show that these present the greatest difficulties for host masses 0.13≲(M/M_⊙)≲ 0.4, i.e., fully convective stars supported by the ideal gas law, and for very nearby hosts. While work can begin later this decade using AO on current telescopes, of order 90 must await 30m-class AO. I present extensive tables with information that is useful to plan observations of more than 100 of these planets and provide additional notes for a majority of these. Applying the same approach to two earlier surveys with 6 and 8 planets, respectively, I find that 11 of these 14 planets already have mass measurements by a variety of techniques. These provide suggestive evidence that planet frequency may be higher for nearby stars, D_L≲ 4 kpc compared to those in or near the Galactic bulge. Finally, I analyze the prospects for making the planet mass-function measurement for the case that current astronomical capabilities are seriously degraded.Andrew Gouldwork_cvoaqm4zobgwpbfyz3uw6h2yqiMon, 26 Sep 2022 00:00:00 GMTLearning to Drop Out: An Adversarial Approach to Training Sequence VAEs
https://scholar.archive.org/work/wouv3qjrq5dgvfm7y65syxy6se
In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the latent space, known as posterior collapse. To mitigate this, state-of-the-art models weaken the powerful decoder by applying uniformly random dropout to the decoder input. We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. We then propose an adversarial training strategy to achieve information-based stochastic dropout. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence modeling performance and the information captured in the latent space.Đorđe Miladinović, Kumar Shridhar, Kushal Jain, Max B. Paulus, Joachim M. Buhmann, Carl Allenwork_wouv3qjrq5dgvfm7y65syxy6seMon, 26 Sep 2022 00:00:00 GMTCombinatorial optimization and reasoning with graph neural networks
https://scholar.archive.org/work/dszclpgdgfgzrnd562tfbceni4
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning, especially graph neural networks (GNNs), as a key building block for combinatorial tasks, either directly as solvers or by enhancing exact solvers. The inductive bias of GNNs effectively encodes combinatorial and relational input due to their invariance to permutations and awareness of input sparsity. This paper presents a conceptual review of recent key advancements in this emerging field, aiming at optimization and machine learning researchers.Quentin Cappart, Didier Chételat, Elias Khalil, Andrea Lodi, Christopher Morris, Petar Veličkovićwork_dszclpgdgfgzrnd562tfbceni4Fri, 23 Sep 2022 00:00:00 GMTAmortized Projection Optimization for Sliced Wasserstein Generative Models
https://scholar.archive.org/work/ppic5wlfava4pabbukqk26zf5i
Seeking informative projecting directions has been an important task in utilizing sliced Wasserstein distance in applications. However, finding these directions usually requires an iterative optimization procedure over the space of projecting directions, which is computationally expensive. Moreover, the computational issue is even more severe in deep learning applications, where computing the distance between two mini-batch probability measures is repeated several times. This nested loop has been one of the main challenges that prevent the usage of sliced Wasserstein distances based on good projections in practice. To address this challenge, we propose to utilize the learning-to-optimize technique or amortized optimization to predict the informative direction of any given two mini-batch probability measures. To the best of our knowledge, this is the first work that bridges amortized optimization and sliced Wasserstein generative models. In particular, we derive linear amortized models, generalized linear amortized models, and non-linear amortized models which are corresponding to three types of novel mini-batch losses, named amortized sliced Wasserstein. We demonstrate the favorable performance of the proposed sliced losses in deep generative modeling on standard benchmark datasets.Khai Nguyen, Nhat Howork_ppic5wlfava4pabbukqk26zf5iFri, 23 Sep 2022 00:00:00 GMTDirected Shortest Paths via Approximate Cost Balancing
https://scholar.archive.org/work/2fdtoc6ptvd2pcrxalmws6vyou
We present an O(nm) algorithm for all-pairs shortest paths computations in a directed graph with n nodes, m arcs, and nonnegative integer arc costs. This matches the complexity bound attained by Thorup for the all-pairs problems in undirected graphs. The main insight is that shortest paths problems with approximately balanced directed cost functions can be solved similarly to the undirected case. The algorithm finds an approximately balanced reduced cost function in an O(m√(n)log n) preprocessing step. Using these reduced costs, every shortest path query can be solved in O(m) time using an adaptation of Thorup's component hierarchy method. The balancing result can also be applied to the ℓ_∞-matrix balancing problem.James B. Orlin, László A. Véghwork_2fdtoc6ptvd2pcrxalmws6vyouThu, 22 Sep 2022 00:00:00 GMTAmortized Variational Inference: Towards the Mathematical Foundation and Review
https://scholar.archive.org/work/lbh5fdiayvhenctvicjrlftm6y
The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box- and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. With this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetaiwork_lbh5fdiayvhenctvicjrlftm6yThu, 22 Sep 2022 00:00:00 GMTStatistical Decoding 2.0: Reducing Decoding to LPN
https://scholar.archive.org/work/gsx5p3qdvzfwxpdtv34kdtucfq
The security of code-based cryptography relies primarily on the hardness of generic decoding with linear codes. The best generic decoding algorithms are all improvements of an old algorithm due to Prange: they are known under the name of information set decoders (ISD). A while ago, a generic decoding algorithm which does not belong to this family was proposed: statistical decoding. It is a randomized algorithm that requires the computation of a large set of parity-checks of moderate weight, and uses some kind of majority voting on these equations to recover the error. This algorithm was long forgotten because even the best variants of it performed poorly when compared to the simplest ISD algorithm. We revisit this old algorithm by using parity-check equations in a more general way. Here the parity-checks are used to get LPN samples with a secret which is part of the error and the LPN noise is related to the weight of the parity-checks we produce. The corresponding LPN problem is then solved by standard Fourier techniques. By properly choosing the method of producing these low weight equations and the size of the LPN problem, we are able to outperform in this way significantly information set decodings at code rates smaller than 0.3. It gives for the first time after 60 years, a better decoding algorithm for a significant range which does not belong to the ISD family.Kevin Carrier, Thomas Debris-Alazard, Charles Meyer-Hilfiger, Jean-Pierre Tillichwork_gsx5p3qdvzfwxpdtv34kdtucfqWed, 21 Sep 2022 00:00:00 GMTBuilding Flexible, Low-Cost Wireless Access Networks With Magma
https://scholar.archive.org/work/l3ya2iieczf5tjvu4adzsercgm
Billions of people remain without Internet access due to availability or affordability of service. In this paper, we present Magma, an open and flexible system for building low-cost wireless access networks. Magma aims to connect users where operator economics are difficult due to issues such as low population density or income levels, while preserving features expected in cellular networks such as authentication and billing policies. To achieve this, and in contrast to traditional cellular networks, Magma adopts an approach that extensively leverages Internet design patterns, terminating access network-specific protocols at the edge and abstracting the access network from the core architecture. This decision allows Magma to refactor the wireless core using SDN (software-defined networking) principles and leverage other techniques from modern distributed systems. In doing so, Magma lowers cost and operational complexity for network operators while achieving resilience, scalability, and rich policy support.Shaddi Hasan, Amar Padmanabhan, Bruce Davie, Jennifer Rexford, Ulas Kozat, Hunter Gatewood, Shruti Sanadhya, Nick Yurchenko, Tariq Al-Khasib, Oriol Batalla, Marie Bremner, Andrei Lee, Evgeniy Makeev, Scott Moeller, Alex Rodriguez, Pravin Shelar, Karthik Subraveti, Sudarshan Kandi, Alejandro Xoconostle, Praveen Kumar Ramakrishnan, Xiaochen Tian, Anoop Tomarwork_l3ya2iieczf5tjvu4adzsercgmTue, 20 Sep 2022 00:00:00 GMTFew-Shot Non-Parametric Learning with Deep Latent Variable Model
https://scholar.archive.org/work/j3jka4jgkzbd7dxlrzvdoc5bsa
Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation. We propose Non-Parametric learning by Compression with Latent Variables (NPC-LV), a learning framework for any dataset with abundant unlabeled data but very few labeled ones. By only training a generative model in an unsupervised way, the framework utilizes the data distribution to build a compressor. Using a compressor-based distance metric derived from Kolmogorov complexity, together with few labeled data, NPC-LV classifies without further training. We show that NPC-LV outperforms supervised methods on all three datasets on image classification in low data regime and even outperform semi-supervised learning methods on CIFAR-10. We demonstrate how and when negative evidence lowerbound (nELBO) can be used as an approximate compressed length for classification. By revealing the correlation between compression rate and classification accuracy, we illustrate that under NPC-LV, the improvement of generative models can enhance downstream classification accuracy.Zhiying Jiang, Yiqin Dai, Ji Xin, Ming Li, Jimmy Linwork_j3jka4jgkzbd7dxlrzvdoc5bsaSat, 17 Sep 2022 00:00:00 GMTSecure and Efficient Query Processing in Outsourced Databases
https://scholar.archive.org/work/ihspi4oagzb4pohhtiph6ica74
Various cryptographic techniques are used in outsourced database systems to ensure data privacy while allowing for efficient querying. This work proposes a definition and components of a new secure and efficient outsourced database system, which answers various types of queries, with different privacy guarantees in different security models. This work starts with the survey of five order-revealing encryption schemes that can be used directly in many database indices and five range query protocols with various security / efficiency tradeoffs. The survey systematizes the state-of-the-art range query solutions in a snapshot adversary setting and offers some non-obvious observations regarding the efficiency of the constructions. In ℰpsolute, a secure range query engine, security is achieved in a setting with a much stronger adversary where she can continuously observe everything on the server, and leaking even the result size can enable a reconstruction attack. ℰpsolute proposes a definition, construction, analysis, and experimental evaluation of a system that provably hides both access pattern and communication volume while remaining efficient. The work concludes with k-anon – a secure similarity search engine in a snapshot adversary model. The work presents a construction in which the security of kNN queries is achieved similarly to OPE / ORE solutions – encrypting the input with an approximate Distance Comparison Preserving Encryption scheme so that the inputs, the points in a hyperspace, are perturbed, but the query algorithm still produces accurate results. We use TREC datasets and queries for the search, and track the rank quality metrics such as MRR and nDCG. For the attacks, we build an LSTM model that trains on the correlation between a sentence and its embedding and then predicts words from the embedding.Dmytro Bogatovwork_ihspi4oagzb4pohhtiph6ica74Sat, 17 Sep 2022 00:00:00 GMTEssays on CEO narcissism and managerial decision-makings
https://scholar.archive.org/work/lasbt6sfhjfbhnykikklhb4tsi
Chief executive officer (CEO) narcissism has emerged as a key predictor of a firm's strategic decision-making. Burgeoning literature rooted in psychology suggests that CEO narcissism, as a 'dark side' personality trait, displays contradictory influences for a firm's strategic outcomes. The current literature suggests that CEO narcissism can be either beneficial or harmful to a firm, depending on various conditions. This highlights many challenges and opportunities for further research. This thesis takes up the challenges and opportunities to examine how and why CEO narcissism matters in strategic decision-making and under what conditions. Specifically, the thesis aims to investigate the microfoundations of narcissistic owner CEOs' influences on a firm's internal decision-making process and decisions on its' external (international) expansion strategies. To explore the influences of CEO narcissism on a firm's internationalisation decisions, the thesis builds on the theoretical perspective of upper echelons theory. To examine how CEO narcissism influences a firm's internal decision-making process, the thesis uses leadership theory to focus on the impact of CEO narcissism on middle managers' divergent strategic behaviour. Four independent studies were carried out to fulfil these thesis aims. Study 1 draws on upper echelons theory and trait activation theory to propose that exporting small-to-medium enterprises (SMEs) with narcissistic owner CEOs are more likely to choose the strategy of market spreading over market concentration, depending on firm-level asset-specific investments and exporting experience. Quantitative data from 248 exporting SMEs in China, accompanied by qualitative data from five case studies, show a significant relationship between owner CEO narcissism and the choice of a market spreading strategy. It also reveals the significant moderating effect of asset-specific investments and firms' exporting experience, supporting the proposed three-way interaction model. Study 2 builds on upper echelons the [...]Xiaoxuan Liwork_lasbt6sfhjfbhnykikklhb4tsiFri, 16 Sep 2022 00:00:00 GMTFast hierarchical low-rank view factor matrices for thermal irradiance on planetary surfaces
https://scholar.archive.org/work/aotcku3blndzldi3lv5rx4xskm
We present an algorithm for compressing the radiosity view factor model commonly used in radiation heat transfer and computer graphics. We use a format inspired by the hierarchical off-diagonal low rank format, where elements are recursively partitioned using a quadtree or octree and blocks are compressed using a sparse singular value decomposition -- the hierarchical matrix is assembled using dynamic programming. The motivating application is time-dependent thermal modeling on vast planetary surfaces, with a focus on permanently shadowed craters which receive energy through indirect irradiance. In this setting, shape models are comprised of a large number of triangular facets which conform to a rough surface. At each time step, a quadratic number of triangle-to-triangle scattered fluxes must be summed; that is, as the sun moves through the sky, we must solve the same view factor system of equations for a potentially unlimited number of time-varying righthand sides. We first conduct numerical experiments with a synthetic spherical cap-shaped crater, where the equilibrium temperature is analytically available. We also test our implementation with triangle meshes of planetary surfaces derived from digital elevation models recovered by orbiting spacecrafts. Our results indicate that the compressed view factor matrix can be assembled in quadratic time, which is comparable to the time it takes to assemble the full view matrix itself. Memory requirements during assembly are reduced by a large factor. Finally, for a range of compression tolerances, the size of the compressed view factor matrix and the speed of the resulting matrix vector product both scale linearly (as opposed to quadratically for the full matrix), resulting in orders of magnitude savings in processing time and memory space.Samuel F. Potter, Stefano Bertone, Norbert Schörghofer, Erwan Mazaricowork_aotcku3blndzldi3lv5rx4xskmThu, 15 Sep 2022 00:00:00 GMTImproving School Education Outcomes in Developing Countries
https://scholar.archive.org/work/etu4dc2ug5dlznf54q6dc4itpy
Improvements in empirical research standards for credible identification of the causal impact of education policies on education outcomes have led to a significant increase in the body of evidence available on improving education outcomes in developing countries. This paper aims to synthesize this evidence, interpret their results, and discuss the reasons why some interventions appear to be effective and others do not, with the ultimate goal of drawing implications for both research and policy. Interpreting the evidence for generalizable lessons is challenging because of variation across contexts, duration and quality of studies, and the details of specific interventions studied. Nevertheless, some broad patterns do emerge. Demand-side interventions that increase the immediate returns to (or reduce household costs of) school enrollment, or that increase students' returns to effort, are broadly effective at increasing time in school and learning outcomes, but vary considerably in cost effectiveness. Many expensive "standard" school inputs are often not very effective at improving outcomes, though some specific inputs (which are often less expensive) are. Interventions that focus on improved pedagogy (especially supplemental instruction to children lagging behind grade level competencies) are particularly effective, and so are interventions that improve school governance and teacher accountability. Our broad policy message is that the evidence points to several promising ways in which the efficiency of education spending in developing countries can be improved by pivoting public expenditure from less cost-effective to more cost-effective ways of achieving the same objectives. We conclude by documenting areas where more research is needed, and offer suggestions on the public goods and standards needed to make it easier for decentralized and uncoordinated research studies to be compared across contexts.Paul Glewwe, Karthik Muralidharanwork_etu4dc2ug5dlznf54q6dc4itpyThu, 15 Sep 2022 00:00:00 GMTA Survey of Machine Unlearning
https://scholar.archive.org/work/bout4zfukrbgzez3zqemxneyjm
Computer systems hold a large amount of personal data over decades. On the one hand, such data abundance allows breakthroughs in artificial intelligence (AI), especially machine learning (ML) models. On the other hand, it can threaten the privacy of users and weaken the trust between humans and AI. Recent regulations require that private information about a user can be removed from computer systems in general and from ML models in particular upon request (e.g. the "right to be forgotten"). While removing data from back-end databases should be straightforward, it is not sufficient in the AI context as ML models often "remember" the old data. Existing adversarial attacks proved that we can learn private membership or attributes of the training data from the trained models. This phenomenon calls for a new paradigm, namely machine unlearning, to make ML models forget about particular data. It turns out that recent works on machine unlearning have not been able to solve the problem completely due to the lack of common frameworks and resources. In this survey paper, we seek to provide a thorough investigation of machine unlearning in its definitions, scenarios, mechanisms, and applications. Specifically, as a categorical collection of state-of-the-art research, we hope to provide a broad reference for those seeking a primer on machine unlearning and its various formulations, design requirements, removal requests, algorithms, and uses in a variety of ML applications. Furthermore, we hope to outline key findings and trends in the paradigm as well as highlight new areas of research that have yet to see the application of machine unlearning, but could nonetheless benefit immensely. We hope this survey provides a valuable reference for ML researchers as well as those seeking to innovate privacy technologies. Our resources are at https://github.com/tamlhp/awesome-machine-unlearning.Thanh Tam Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, Quoc Viet Hung Nguyenwork_bout4zfukrbgzez3zqemxneyjmMon, 12 Sep 2022 00:00:00 GMTEfficient computation of the Wright function and its applications to fractional diffusion-wave equations
https://scholar.archive.org/work/cnpqm73xofb3tbbq5y5d5aixt4
In this article, we deal with the efficient computation of the Wright function in the cases of interest for the expression of solutions of some fractional differential equations. The proposed algorithm is based on the inversion of the Laplace transform of a particular expression of the Wright function for which we discuss in detail the error analysis. We also present a code package that implements the algorithm proposed here in different programming languages. The analysis and implementation are accompanied by an extensive set of numerical experiments that validate both the theoretical estimates of the error and the applicability of the proposed method for representing the solutions of fractional differential equations.Lidia Aceto, Fabio Durastantework_cnpqm73xofb3tbbq5y5d5aixt4Mon, 12 Sep 2022 00:00:00 GMTA Review of Multi-Modal Learning from the Text-Guided Visual Processing Viewpoint
https://scholar.archive.org/work/p6ofbm27fjevfihxogr7kc7s2m
For decades, co-relating different data domains to attain the maximum potential of machines has driven research, especially in neural networks. Similarly, text and visual data (images and videos) are two distinct data domains with extensive research in the past. Recently, using natural language to process 2D or 3D images and videos with the immense power of neural nets has witnessed a promising future. Despite the diverse range of remarkable work in this field, notably in the past few years, rapid improvements have also solved future challenges for researchers. Moreover, the connection between these two domains is mainly subjected to GAN, thus limiting the horizons of this field. This review analyzes Text-to-Image (T2I) synthesis as a broader picture, Text-guided Visual-output (T2Vo), with the primary goal being to highlight the gaps by proposing a more comprehensive taxonomy. We broadly categorize text-guided visual output into three main divisions and meaningful subdivisions by critically examining an extensive body of literature from top-tier computer vision venues and closely related fields, such as machine learning and human–computer interaction, aiming at state-of-the-art models with a comparative analysis. This study successively follows previous surveys on T2I, adding value by analogously evaluating the diverse range of existing methods, including different generative models, several types of visual output, critical examination of various approaches, and highlighting the shortcomings, suggesting the future direction of research.Ubaid Ullah, Jeong-Sik Lee, Chang-Hyeon An, Hyeonjin Lee, Su-Yeong Park, Rock-Hyun Baek, Hyun-Chul Choiwork_p6ofbm27fjevfihxogr7kc7s2mThu, 08 Sep 2022 00:00:00 GMTSome models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
https://scholar.archive.org/work/rixwf3eo6baltbfhkgpw25kfn4
Probabilistic (Bayesian) modeling has experienced a surge of applications in almost all quantitative sciences and industrial areas. This development is driven by a combination of several factors, including better probabilistic estimation algorithms, flexible software, increased computing power, and a growing awareness of the benefits of probabilistic learning. However, a principled Bayesian model building workflow is far from complete and many challenges remain. To aid future research and applications of a principled Bayesian workflow, we ask and provide answers for what we perceive as two fundamental questions of Bayesian modeling, namely (a) "What actually is a Bayesian model?" and (b) "What makes a good Bayesian model?". As an answer to the first question, we propose the PAD model taxonomy that defines four basic kinds of Bayesian models, each representing some combination of the assumed joint distribution of all (known or unknown) variables (P), a posterior approximator (A), and training data (D). As an answer to the second question, we propose ten utility dimensions according to which we can evaluate Bayesian models holistically, namely, (1) causal consistency, (2) parameter recoverability, (3) predictive performance, (4) fairness, (5) structural faithfulness, (6) parsimony, (7) interpretability, (8) convergence, (9) estimation speed, and (10) robustness. Further, we propose two example utility decision trees that describe hierarchies and trade-offs between utilities depending on the inferential goals that drive model building and testing.Paul-Christian Bürkner and Maximilian Scholz and Stefan T. Radevwork_rixwf3eo6baltbfhkgpw25kfn4Wed, 07 Sep 2022 00:00:00 GMT