IA Scholar Query: On the Complexity of Graph-Based Bounds for the Probability Bounding Problem.
https://scholar.archive.org/
Internet Archive Scholar query results feedeninfo@archive.orgSat, 31 Dec 2022 00:00:00 GMTfatcat-scholarhttps://scholar.archive.org/help1440A Weakly Reiterative Patches-Wise Framework for CT Liver and Lesions Segmentation
https://scholar.archive.org/work/kpceizq4ejawvp3yzyvatms2wa
Automatic Liver and lesions segmentation from volumetric computerized tomography scans has been recently an active research area in images processing field. An accurate automatic segmentation is helpful to make personalized treatment schemes and have a big impact on liver therapy planning. However, it stays a challenging task due to similar pixel intensity of liver lesions with their surrounding tissues, fuzzy borders, diverse densities, and the big variety of size, position, and shape features of liver and lesions. Recently, deep learning achieved the state of art performance in many computers vision tasks. Nevertheless, it's heavy rely on huge amount of labelled data. In medical images semantic segmentation, data annotation is time consuming and expensive to require. In this paper we propose a new framework for Liver and lesions segmentation using a weakly cascaded reiterative patches-wise convolutional neural network. A first model is used to localize object of interest and reduce the scope, the result is feed then as ROI in a second tuning network for final segmentation. To overcome the conventional methods drawbacks and provides greater retention of fine details, a multi-level patches wise training is proposed. Different dilated convolutional kernels sizes with are used in the encoder first layer to derive abundant semantic contextual features from CT scans. We also propose a new multi-level loss function for high precision. The proposed approach achieved a mean IoU score of 0,9511 for liver and 0,9471 for lesions segmentation.work_kpceizq4ejawvp3yzyvatms2waSat, 31 Dec 2022 00:00:00 GMTA Survey on Concept Drift in Process Mining
https://scholar.archive.org/work/hvmkupdorzf5df4tts42gzykjm
Concept drift in process mining (PM) is a challenge as classical methods assume processes are in a steady-state, i.e., events share the same process version. We conducted a systematic literature review on the intersection of these areas, and thus, we review concept drift in PM and bring forward a taxonomy of existing techniques for drift detection and online PM for evolving environments. Existing works depict that (i) PM still primarily focuses on offline analysis, and (ii) the assessment of concept drift techniques in processes is cumbersome due to the lack of common evaluation protocol, datasets, and metrics.Denise Maria Vecino Sato, Sheila Cristiana De Freitas, Jean Paul Barddal, Edson Emilio Scalabrinwork_hvmkupdorzf5df4tts42gzykjmSat, 31 Dec 2022 00:00:00 GMTComputing Graph Neural Networks: A Survey from Algorithms to Accelerators
https://scholar.archive.org/work/7uww2lnxrbdpnnyvzsanojgnba
Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data. Such an ability has strong implications in a wide variety of fields whose data are inherently relational, for which conventional neural networks do not perform well. Indeed, as recent reviews can attest, research in the area of GNNs has grown rapidly and has lead to the development of a variety of GNN algorithm variants as well as to the exploration of ground-breaking applications in chemistry, neurology, electronics, or communication networks, among others. At the current stage research, however, the efficient processing of GNNs is still an open challenge for several reasons. Besides of their novelty, GNNs are hard to compute due to their dependence on the input graph, their combination of dense and very sparse operations, or the need to scale to huge graphs in some applications. In this context, this article aims to make two main contributions. On the one hand, a review of the field of GNNs is presented from the perspective of computing. This includes a brief tutorial on the GNN fundamentals, an overview of the evolution of the field in the last decade, and a summary of operations carried out in the multiple phases of different GNN algorithm variants. On the other hand, an in-depth analysis of current software and hardware acceleration schemes is provided, from which a hardware-software, graph-aware, and communication-centric vision for GNN accelerators is distilled.Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, Eduard Alarcónwork_7uww2lnxrbdpnnyvzsanojgnbaSat, 31 Dec 2022 00:00:00 GMTObstacle Avoidance and Path Planning for UAV Using Laguerre Polynomial
https://scholar.archive.org/work/orzu4j3vxnbxrjsu36dovkv4yi
Recently, path planning algorithms have been one of the primary and important functions of unmanned aerial vehicles (UAVs). Path planning algorithms in UAVs focused on path length, average path length, computation time, and standard deviation from the mean path length. In spite of this, it faced many difficulties and problems, such as many obstacles, path segmentation, and the increasing number of obstacles and paths in urban environments. This work proposes polynomial functions for path planning and obstacle avoidance. Since it enables us to plan the path in static internal environments, it enables us to plan the path quickly and with less computing time because it does not require high memory and does not require pre-compute of the path. Instead, the route is plotted in real time, Where the appropriate equation is entered into the program, so that the vehicle follows the curve of the entered equation. An accurate data set and metrics were used to measure the efficiency of the proposed method. The experimental results showed a clear improvement in the work of the polynomial function on A*, PSO and genetic algorithms, as this improvement appears very clearly when compared to the computing time, which was reduced by 15% in the method of polynomial functions where the path calculation took only parts of The second, as well as the path length was halved in the polynomial method as the results showed, which reduces the time of battery and memory consumption, the cost of calculating the path and the time to reach the goal.work_orzu4j3vxnbxrjsu36dovkv4yiSat, 31 Dec 2022 00:00:00 GMTArbitrary Oriented Scene Text Recognizer (AOTR)
https://scholar.archive.org/work/62cimrwsufgrrivw2uwvl3tmhy
Recognizing arbitrary oriented text has grabbed researchers' attention to develop several algorithms due to its high complexity in scene images and real-time applications like language translators, reading text for blind people, navigation systems, and smart parking. Converting text in natural scene images into strings has extended its application to Natural Language Processing (NLP)-based applications like named entity recognition. There are only three methods for text recognition: Optical Character Recognition (OCR), conventional methods, and Neural Network (NN) models. OCR is only known to be a successful text recognizer for scanned images, and in recent years, NN models have outperformed traditional methods for scene text recognition. It is necessary to create an optimal model to address the issue of scene text irregularity. We present the NN and customized OCR models, which we tailor for arbitrarily oriented text recognition, thereby avoiding scene text irregularity. An Orientation Correction Model (OCM) was introduced to improve the recognition model. In place of the recognition model, we used OCR. Alternatively, we created another model that reads corrected text images and extracts low-level features using the convolutional neural network layer. A recurrent neural network then uses these features to recognize text. Experiments were conducted on ICDAR2015, Total Text, Art19, and Cute80 benchmark datasets. It is observed that the proposed model obtains 79.5 % accuracy and hence increases the result by 1.9 % compared to the existing method after adding the orientation correction model. Similarly, results are promising on other datasets compared to existing algorithms.work_62cimrwsufgrrivw2uwvl3tmhySat, 31 Dec 2022 00:00:00 GMT1 Introduction: What is World History?
https://scholar.archive.org/work/y34ec6qcdrbkrjpb6iy3wz5nxq
The aim of the chapter is to introduce the student to the academic study of history, by presenting three core concepts which are part of the traditions in the field, before moving on to discuss the World History approach and its distinctive features.Isabelle Duyvesteyn, Anne Marieke van der Walwork_y34ec6qcdrbkrjpb6iy3wz5nxqSat, 31 Dec 2022 00:00:00 GMTLearning Unsupervised Hierarchies of Audio Concepts
https://scholar.archive.org/work/gojab4eqqrf35csqhposiyl27y
Music signals are difficult to interpret from their low-level features, perhaps even more than images: e.g. highlighting part of a spectrogram or an image is often insufficient to convey high-level ideas that are genuinely relevant to humans. In computer vision, concept learning was therein proposed to adjust explanations to the right abstraction level (e.g. detect clinical concepts from radiographs). These methods have yet to be used for MIR.In this paper, we adapt concept learning to the realm of music, with its particularities. For instance, music concepts are typically non-independent and of mixed nature (e.g. genre, instruments, mood), unlike previous work that assumed disentangled concepts.We propose a method to learn numerous music concepts from audio and then automatically hierarchise them to expose their mutual relationships. We conduct experiments on datasets of playlists from a music streaming service, serving as a few annotated examples for diverse concepts. Evaluations show that the mined hierarchies are aligned with both ground-truth hierarchies of concepts -- when available -- and with proxy sources of concept similarity in the general case.Darius Afchar, Romain Hennequin, Vincent Guiguework_gojab4eqqrf35csqhposiyl27ySun, 04 Dec 2022 00:00:00 GMTDistinguish between Stochastic and Chaotic Signals by a Local Structure-Based Entropy
https://scholar.archive.org/work/fm3x7gt7i5dmxmp3hu2ifkbvqa
As a measure of complexity, information entropy is frequently used to categorize time series, such as machinery failure diagnostics, biological signal identification, etc., and is thought of as a characteristic of dynamic systems. Many entropies, however, are ineffective for multivariate scenarios due to correlations. In this paper, we propose a local structure entropy (LSE) based on the idea of a recurrence network. Given certain tolerance and scales, LSE values can distinguish multivariate chaotic sequences between stochastic signals. Three financial market indices are used to evaluate the proposed LSE. The results show that the LSEFSTE100 and LSES&P500 are higher than LSESZI, which indicates that the European and American stock markets are more sophisticated than the Chinese stock market. Additionally, using decision trees as the classifiers, LSE is employed to detect bearing faults. LSE performs higher on recognition accuracy when compared to permutation entropy.Zelin Zhang, Jun Wu, Yufeng Chen, Ji Wang, Jinyu Xuwork_fm3x7gt7i5dmxmp3hu2ifkbvqaWed, 30 Nov 2022 00:00:00 GMTComputing Divergences between Discrete Decomposable Models
https://scholar.archive.org/work/7jsyfyyhnnaupnjkd3odsnx35q
There are many applications that benefit from computing the exact divergence between 2 discrete probability measures, including machine learning. Unfortunately, in the absence of any assumptions on the structure or independencies within these distributions, computing the divergence between them is an intractable problem in high dimensions. We show that we are able to compute a wide family of functionals and divergences, such as the alpha-beta divergence, between two decomposable models, i.e. chordal Markov networks, in time exponential to the treewidth of these models. The alpha-beta divergence is a family of divergences that include popular divergences such as the Kullback-Leibler divergence, the Hellinger distance, and the chi-squared divergence. Thus, we can accurately compute the exact values of any of this broad class of divergences to the extent to which we can accurately model the two distributions using decomposable models.Loong Kuan Lee, Nico Piatkowski, François Petitjean, Geoffrey I. Webbwork_7jsyfyyhnnaupnjkd3odsnx35qWed, 30 Nov 2022 00:00:00 GMTTrifocal Relative Pose from Lines at Points and its Efficient Solution
https://scholar.archive.org/work/zkhnt5hqhrejffrptitosf3zt4
We present a method for solving two minimal problems for relative camera pose estimation from three views, which are based on three view correspondences of i) three points and one line and the novel case of ii) three points and two lines through two of the points. These problems are too difficult to be efficiently solved by the state of the art Groebner basis methods. Our method is based on a new efficient homotopy continuation (HC) solver framework MINUS, which dramatically speeds up previous HC solving by specializing HC methods to generic cases of our problems. We characterize their number of solutions and show with simulated experiments that our solvers are numerically robust and stable under image noise, a key contribution given the borderline intractable degree of nonlinearity of trinocular constraints. We show in real experiments that i) SIFT feature location and orientation provide good enough point-and-line correspondences for three-view reconstruction and ii) that we can solve difficult cases with too few or too noisy tentative matches, where the state of the art structure from motion initialization fails.Ricardo Fabbri, Timothy Duff, Hongyi Fan, Margaret Regan, David da Costa de Pinho, Elias Tsigaridas, Charles Wampler, Jonathan Hauenstein, Benjamin Kimia, Anton Leykin, Tomas Pajdlawork_zkhnt5hqhrejffrptitosf3zt4Wed, 30 Nov 2022 00:00:00 GMTConjunctive queries for logic-based information extraction
https://scholar.archive.org/work/wd2pb3qomzeb7lqcc3av3fepqq
This thesis offers two logic-based approaches to conjunctive queries in the context of information extraction. The first and main approach is the introduction of conjunctive query fragments of the logics FC and FC[REG], denoted as FC-CQ and FC[REG]-CQ respectively. FC is a first-order logic based on word equations, where the semantics are defined by limiting the universe to the factors of some finite input word. FC[REG] is FC extended with regular constraints. Our first results consider the comparative expressive power of FC[REG]-CQ in relation to document spanners (a formal framework for the query language AQL), and various fragments of FC[REG]-CQ – some of which coincide with well-known language generators, such as patterns and regular expressions. Then, we look at decision problems. We show that many decision problems for FC-CQ and FC[REG]-CQ (such as equivalence and regularity) are undecidable. The model checking problem for FC-CQ and FC[REG]-CQ is NP-complete even if the FC-CQ is acyclic – under the definition of acyclicity where each word equation in an FC-CQ is an atom. This leads us to look at the "decomposition" of an FC word equation into a conjunction of binary word equations (i.e., of the form x =˙ y · z). If a query consists of only binary word equations and the query is acyclic, then model checking is tractable and we can enumerate results efficiently. We give an algorithm that decomposes an FC-CQ into an acyclic FC-CQ consisting of binary word equations in polynomial time, or determines that this is not possible. The second approach is to consider the dynamic complexity of FC. This uses the common way of encoding words in a relational structure using a universe with a linear order along with symbol predicates. Then, each element of the universe can carry a symbol if the predicate for said symbol holds for that element. Instead of the "usual way" (looking at first-order logic over these structures), we study the dynamic complexity, where symbols can be modified. As each of these modifications only c [...]Sam M Thompsonwork_wd2pb3qomzeb7lqcc3av3fepqqWed, 30 Nov 2022 00:00:00 GMTTransdermal Penetration of Photoluminescent Nanoparticles in Human Skin
https://scholar.archive.org/work/fbbagqhjfjfjhnd6kgj3ev4oly
Applications of nanomaterials in cosmetics and pharmaceutical industries raise safety concerns due to their potential penetration into skin. Skin outermost layer, stratum corneum (SC), is an effective barrier for extraneous compounds stopping these materials from entering viable epidermis (VE) and concomitantly systemic circulation of the body. At the same time, transdermal delivery of drugs and cosmetic ingredients critically relies on the enhanced penetration of nanomaterials through skin. This thesis addresses both nanotoxicology and transdermal delivery aspects of nanoparticle interaction with skin. It is consented that ZnO NPs in sunscreens do not penetrate intact skin. However, it has been reported that sunscreens containing ZnO NPs increase zinc ions (Zn2+) levels within VE due to the dissolution of ZnO NPs and releasing Zn species. An excess of zinc (Zn) may be toxic to mammalian cells and organisms, demanding quantitative assessment of Zn accumulation in VE. At the same time, quantification of exogenous trace elements (Zn) in skin, containing exogenous trace elements, is challenging. In order to address this problem systematically, skin absorption of zinc from sunscreen was quantified via an ion coupled plasma mass spectrometry (ICP-MS) and laser-ablation ICP-MS (LA-ICP-MS) techniques. In addition, a sunscreen formulation containing a rare stable isotope of Zn (67Zn) with a natural abundance of 4.04% was used to discriminate sunscreen-derived Zn from endogenous zinc in skin. Assayed concentration of Zn in VE was found to be 1.0 ± 0.3 mg/mL, which was much lower than the potentially cytotoxic labile 67Zn concentrations of 21 – 31 mg/mL. This research speaks strongly in favour of the safety of ZnO NP sunscreens and is expected to be impactful in the field of nanotoxicology. Precise evaluation and monitoring uptake of trace elements in biological samples is a crucial and challenging task as oftentimes organ tissues and cells contain high concentrations of trace elements naturally, which results in eclipsing [...]Zahra Khabirwork_fbbagqhjfjfjhnd6kgj3ev4olyWed, 30 Nov 2022 00:00:00 GMTTowards Covalent Approaches to Stabilise 14-3-3σ Protein-Protein Interactions as a Therapeutic Modality for Cancer
https://scholar.archive.org/work/lwiz2x7fefbkbhq62v3kfpppze
14-3-3 proteins are a ubiquitous family of proteins that play an essential role in cellular homeostasis1,2. They interact with over 200 proteins to modulate their activity, protein folding, subcellular localisation and their interaction with other protein partners3,4. Among 14-3-3 interacting partners are important pharmaceutical targets such as CFTR5, p536, ERα7, Tau8, and LRRK29 that are involved in various diseases such as cystic fibrosis5, cancer10–13 and neurodegenerative diseases14–18. Moreover, 14-3-3 proteins were reported as one of nine key host proteins during SARS CoV-2 infection19. For these reasons, 14-3-3 Protein-Protein Interactions (PPIs) have great potential as novel drug targets and selective stabilisation of 14-3-3 PPIs by using 'molecular glues' would therefore have a significant impact in terms of therapeutic development in many fields of medicine. This work shows that WR-1065 (3), the active species of the approved drug amifostine (AM; 2)20, covalently modifies 14-3-3σ at an isoform-unique residue, Cys38 (Figure 1). This modification leads to isoform specific stabilisation of two 14-3-3σ PPIs (with p53 and the oestrogen receptor α (ERα)) in a manner that is cooperative with a well characterised molecular glue, fusicoccin A21 (FC-A, 1; Figure 1). A novel stabilisation mechanism for 14-3-3σ, an isoform strongly implicated in cancer, was revealed, and this is likely to contribute to the in vivo pharmacodynamics of amifostine. Here, the cellular relevance of the two ligands has been demonstrated in two cancer cell lines where the cooperative behaviour of 1 and 3 leads to enhanced efficacy for inducing cell death and attenuating cell growth. New WR-1065 analogues bearing different electrophilic 'warheads' have been also synthesised and some of them exhibit a ERα/14-3-3σ stabilisation effect. This represents the starting point for the development of new sel [...]Marta Falcicchiowork_lwiz2x7fefbkbhq62v3kfpppzeWed, 30 Nov 2022 00:00:00 GMTOn the complexity of quantum link prediction in complex networks
https://scholar.archive.org/work/omd7afyayzaqvdaydvud3bmu7q
Link prediction methods use patterns in known network data to infer which connections may be missing. Previous work has shown that continuous-time quantum walks can be used to represent path-based link prediction, which we further study here to develop a more optimized quantum algorithm. Using a sampling framework for link prediction, we analyze the query access to the input network required to produce a certain number of prediction samples. Considering both well-known classical path-based algorithms using powers of the adjacency matrix as well as our proposed quantum algorithm for path-based link prediction, we argue that there is a polynomial quantum advantage on the dependence on N, the number of nodes in the network. We further argue that the complexity of our algorithm, although sub-linear in N, is limited by the complexity of performing a quantum simulation of the network's adjacency matrix, which may prove to be an important problem in the development of quantum algorithms for network science in general.João P. Moutinho, Duarte Magano, Bruno Coutinhowork_omd7afyayzaqvdaydvud3bmu7qWed, 30 Nov 2022 00:00:00 GMTBayesian order identification of ARMA models with projection predictive inference
https://scholar.archive.org/work/bdvutc3hh5f6rla7r4dosfkqna
Auto-regressive moving-average (ARMA) models are ubiquitous forecasting tools. Parsimony in such models is highly valued for their interpretability and computational tractability, and as such the identification of model orders remains a fundamental task. We propose a novel method of ARMA order identification through projection predictive inference, which is grounded in Bayesian decision theory and naturally allows for uncertainty communication. It benefits from improved stability through the use of a reference model. The procedure consists of two steps: in the first, the practitioner incorporates their understanding of underlying data-generating process into a reference model, which we latterly project onto possibly parsimonious submodels. These submodels are optimally inferred to best replicate the predictive performance of the reference model. We further propose a search heuristic amenable to the ARMA framework. We show that the submodels selected by our procedure exhibit predictive performance at least as good as those produced by auto.arima over simulated and real-data experiments, and in some cases out-perform the latter. Finally we show that our procedure is robust to noise, and scales well to larger data.Yann McLatchie, Asael Alonzo Matamoros, David Kohns, Aki Vehtariwork_bdvutc3hh5f6rla7r4dosfkqnaWed, 30 Nov 2022 00:00:00 GMTA–E
https://scholar.archive.org/work/enoy33f5ejdntgmhbnitknxxlu
He gained a national reputation with the Viipuri Municipal Library , destroyed in World War II, and an international one with his Finnish pavilions at the World's Fairs at Paris (1937) and New York (1939-40). He made imaginative use of wood with brickwork, glass, copper and cement and also developed functional plywood furniture, mass-produced in his own factory. His range of commissions, including the Maison Carré in Paris, Baker House in Cambridge, Mass., and the Finlandia Concert Hall, Helsinki, was extensive: factories, museums, churches, theatres, department stores, private houses and public housing. He was professor of architecture at the Massachusetts Institute of Technology 1945-49. Aaron (c.14th-13th centuries BCE). Hebrew High Priest. In the Bible story, with his brother *Moses, he led the Israelites from Egypt to Canaan (Palestine) and became their first high priest, but while Moses was receiving the Ten Commandments on Mount Sinai he made a golden calf for the people to worship (Exodus xxiii).work_enoy33f5ejdntgmhbnitknxxluWed, 30 Nov 2022 00:00:00 GMTReinforcement Learning with Dynamic Convex Risk Measures
https://scholar.archive.org/work/k7vmgnmfuvgflattu4provllqi
We develop an approach for solving time-consistent risk-sensitive stochastic optimization problems using model-free reinforcement learning (RL). Specifically, we assume agents assess the risk of a sequence of random variables using dynamic convex risk measures. We employ a time-consistent dynamic programming principle to determine the value of a particular policy, and develop policy gradient update rules that aid in obtaining optimal policies. We further develop an actor-critic style algorithm using neural networks to optimize over policies. Finally, we demonstrate the performance and flexibility of our approach by applying it to three optimization problems: statistical arbitrage trading strategies, financial hedging, and obstacle avoidance robot control.Anthony Coache, Sebastian Jaimungalwork_k7vmgnmfuvgflattu4provllqiWed, 30 Nov 2022 00:00:00 GMTEnhanced Firefly-K-Means Clustering with Adaptive Mutation and Central Limit Theorem for Automatic Clustering of High-Dimensional Datasets
https://scholar.archive.org/work/ispbdfmvmjdrbkmqa4oeixqrdq
Metaheuristic algorithms have been hybridized with the standard K-means to address the latter's challenges in finding a solution to automatic clustering problems. However, the distance calculations required in the standard K-means phase of the hybrid clustering algorithms increase as the number of clusters increases, and the associated computational cost rises in proportion to the dataset dimensionality. The use of the standard K-means algorithm in the metaheuristic-based K-means hybrid algorithm for the automatic clustering of high-dimensional real-world datasets poses a great challenge to the clustering performance of the resultant hybrid algorithms in terms of computational cost. Reducing the computation time required in the K-means phase of the hybrid algorithm for the automatic clustering of high-dimensional datasets will inevitably reduce the algorithm's complexity. In this paper, a preprocessing phase is introduced into the K-means phase of an improved firefly-based K-means hybrid algorithm using the concept of the central limit theorem to partition the high-dimensional dataset into subgroups of randomly formed subsets on which the K-means algorithm is applied to obtain representative cluster centers for the final clustering procedure. The enhanced firefly algorithm (FA) is hybridized with the CLT-based K-means algorithm to automatically determine the optimum number of cluster centroids and generate corresponding optimum initial cluster centroids for the K-means algorithm to achieve optimal global convergence. Twenty high-dimensional datasets from the UCI machine learning repository are used to investigate the performance of the proposed algorithm. The empirical results indicate that the hybrid FA-K-means clustering method demonstrates statistically significant superiority in the employed performance measures and reducing computation time cost for clustering high-dimensional dataset problems, compared to other advanced hybrid search variants.Abiodun M. Ikotun, Absalom E. Ezugwuwork_ispbdfmvmjdrbkmqa4oeixqrdqWed, 30 Nov 2022 00:00:00 GMTExecution Order Matters in Greedy Algorithms with Limited Information
https://scholar.archive.org/work/2xkft5ocgjexpmwbf6ed5yevba
In this work, we study the multi-agent decision problem where agents try to coordinate to optimize a given system-level objective. While solving for the global optimal is intractable in many cases, the greedy algorithm is a well-studied and efficient way to provide good approximate solutions - notably for submodular optimization problems. Executing the greedy algorithm requires the agents to be ordered and execute a local optimization based on the solutions of the previous agents. However, in limited information settings, passing the solution from the previous agents may be nontrivial, as some agents may not be able to directly communicate with each other. Thus the communication time required to execute the greedy algorithm is closely tied to the order that the agents are given. In this work, we characterize interplay between the communication complexity and agent orderings by showing that the complexity using the best ordering is O(n) and increases considerably to O(n^2) when using the worst ordering. Motivated by this, we also propose an algorithm that can find an ordering and execute the greedy algorithm quickly, in a distributed fashion. We also show that such an execution of the greedy algorithm is advantageous over current methods for distributed submodular maximization.Rohit Konda, David Grimsman, Jason Mardenwork_2xkft5ocgjexpmwbf6ed5yevbaWed, 30 Nov 2022 00:00:00 GMTZero-Shot Assistance in Sequential Decision Problems
https://scholar.archive.org/work/r6fgacfyxfhctgnbe32qrvbmba
We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent as in current automation-based approaches, we give the assistant an advisory role and keep the agent in the loop as the main decision maker. The difficulty is that we must account for potential biases of the agent which may cause it to seemingly irrationally reject advice. To do this we introduce a novel formalization of assistance that models these biases, allowing the assistant to infer and adapt to them. We then introduce a new method for planning the assistant's actions which can scale to large decision making problems. We show experimentally that our approach adapts to these agent biases, and results in higher cumulative reward for the agent than automation-based alternatives. Lastly, we show that an approach combining advice and automation outperforms advice alone at the cost of losing some safety guarantees.Sebastiaan De Peuter, Samuel Kaskiwork_r6fgacfyxfhctgnbe32qrvbmbaWed, 30 Nov 2022 00:00:00 GMT