Filters








93 Hits in 8.3 sec

Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting [article]

Keyi Chen, John Langford, Francesco Orabona
2022 arXiv   pre-print
In this paper, we close the empirical gap with a new parameter-free algorithm based on continuous-time Coin-Betting on truncated models.  ...  Parameter-free stochastic gradient descent (PFSGD) algorithms do not require setting learning rates while achieving optimal theoretical performance.  ...  "AF: Small: Collaborative Research: New Representations for Learning Algorithms and Secure Computation", and no. 2046096 "CAREER: Parameter-free Optimization Algorithms for Machine Learning".  ... 
arXiv:2006.07507v3 fatcat:7phhzpv76zgsjbepx4cbzdlaz4

Implicit Parameter-free Online Learning with Truncated Linear Models [article]

Keyi Chen and Ashok Cutkosky and Francesco Orabona
2022 arXiv   pre-print
Unfortunately, truncated linear models cannot be used with parameter-free algorithms because the updates become very expensive to compute.  ...  Recently, in the stochastic optimization literature, it has been proposed to instead use truncated linear lower bounds, which produce better performance by more closely modeling the losses.  ...  and Secure Computation" and no. 2046096 "CAREER: Parameter-free Optimization Algorithms for Machine Learning".  ... 
arXiv:2203.10327v1 fatcat:tgdm7kp2rzgslgjtsvxeze3ibi

Reaction norms with bifurcations shaped by evolution

T. J. M. van Dooren
2001 Proceedings of the Royal Society of London. Biological Sciences  
The evolutionary trajectory becomes trapped in a local selective optimum for the parameters of the developmental system.  ...  In the second model version, branching reaction norms occur for certain parameter combinations of the developmental submodel, but the evolution of this pattern is often constrained.  ...  In the context of stochastic strategies, it remains a major issue to determine how individuals hedge their bets. How do they perform adaptive coin £ipping (Kaplan & Cooper 1984) ?  ... 
doi:10.1098/rspb.2000.1362 pmid:11217899 pmcid:PMC1088604 fatcat:tz66ge7yqvgr5j562vxiabnjoe

Optimal Parameter-free Online Learning with Switching Cost [article]

Zhiyu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
2022 arXiv   pre-print
Parameter-freeness in online learning refers to the adaptivity of an algorithm with respect to the optimal decision in hindsight.  ...  Based on a novel dual space scaling strategy, we propose a simple yet powerful algorithm for Online Linear Optimization (OLO) with switching cost, which improves the existing suboptimal regret bound [ZCP22a  ...  Coin-betting is essentially derived from certain types of potentials [OP16] , and many theoretical results using coin-betting can be recovered by the latter.  ... 
arXiv:2205.06846v2 fatcat:nyduotl32bc4tftmyucmvabcni

Deep Reinforcement Learning, a textbook [article]

Aske Plaat
2022 arXiv   pre-print
The book is written for graduate students of artificial intelligence, and for researchers and practitioners who wish to better understand deep reinforcement learning methods and their challenges.  ...  We cover the established model-free and model-based methods that form the basis of the field.  ...  All functions are parameterized with their own set of parameters.  ... 
arXiv:2201.02135v2 fatcat:3icsopexerfzxa3eblpu5oal64

The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning [article]

Raed Kontar, Naichen Shi, Xubo Yue, Seokhyun Chung, Eunshin Byon, Mosharaf Chowdhury, Judy Jin, Wissam Kontar, Neda Masoud, Maher Noueihed, Chinedum E. Okwudire, Garvesh Raskutti (+3 others)
2021 arXiv   pre-print
This article provides a vision for IoFT and a systematic overview of current efforts towards realizing this vision.  ...  This paradigm shift was set into motion by the tremendous increase in computational power on IoT devices and the recent advances in decentralized and privacy-preserving model training, coined as federated  ...  With proper hyper-parameter by alternating optimization methods.  ... 
arXiv:2111.05326v1 fatcat:bbgdhtuqcrhstgakt2vxuve2ca

A Review of Mathematical and Computational Methods in Cancer Dynamics [article]

Abicumaran Uthamacumaran, Hector Zenil
2022 arXiv   pre-print
To conclude, the perspective cultivates an intuition for computational systems oncology in terms of nonlinear dynamics, information theory, inverse problems and complexity.  ...  We highlight the limitations we see in the area of statistical machine learning but the opportunity at combining it with the symbolic computational power offered by the mathematical tools explored.  ...  Jacek Majewski of McGill University, for the knowledge he granted on glioma epigenetics and computational epigenetic modelling.  ... 
arXiv:2201.02055v5 fatcat:hxhvnvagcbdeldwsb3zet3wavu

Evaluating Product Plans Using Real Options

Prasenjit Shil, Venkat Allada
2007 The Engineering Economist  
Allada variant should be discontinued, scaled down, or scaled up with additional product features.  ...  Platform "500" was updated several times with new features and technology to meet the customer demands.  ...  Such stochastic phenomenon can be mathematically modeled as geometric Brownian motion Table 2 . 2 Basic parameters to evaluate financial options and real options Financial options Real options  ... 
doi:10.1080/00137910701504058 fatcat:y63o7xvrvjekhnmoujis4bhpym

Modelling change in supply-chain-structures and its effect on freight transport demand

Ole Ottemöller, Hanno Friedrich
2017 Transportation Research Part E: Logistics and Transportation Review  
Here, the model applies a combination of stochastic simulation, linear programming, and fitting procedures.  ...  actual manufacturing processes are bound to specialised business establishments, which are only partially dispersed across space, commodity flows are required that connect locations of excess supply with  ...  This second step can stochastic location macro allocation stochastic location optimal allocation optimal location optimal allocation assumptions freight transport performance Stochastic Location and  ... 
doi:10.1016/j.tre.2017.08.009 fatcat:f77eqsmjlraynlv7hgrod3657y

Backward Chaining [chapter]

2013 Encyclopedia of Operations Research and Management Science  
For risk-free cashflows, the appropriate discount rate is the rate implied by the Treasury yield curve.  ...  One major strand of research is devoted to the development of stochastic models for the term structure of interest rates.  ...  Such a bet is called a dutch book.  ... 
doi:10.1007/978-1-4419-1153-7_200968 fatcat:wsdsqf2wxrckvpoq4yh5f7rsqm

Multi-agent online learning in time-varying games [article]

Benoit Duvocelle and Panayotis Mertikopoulos and Mathias Staudigl and Dries Vermeulen
2021 arXiv   pre-print
Acknowledgments This research was partially supported by the COST Action CA16228 "European Network for Game Theory" (GAMENET). P.  ...  Mertikopoulos is grateful for financial support by the French National Research Agency (ANR) in the framework of the "Investissements d'avenir" program (ANR-15-IDEX-02), the LabEx PERSYVAL (ANR-11-LABX  ...  [30] proposed a meta-aggregator based on coin betting, while Jadbabaie et al. [28] and Shahrampour and Jadbabaie [53] take an approach based on optimistic mirror descent.  ... 
arXiv:1809.03066v3 fatcat:pbbixcut5jgzfp74f5guxztb5u

Parameter Estimation, Model Reduction and Quantum Filtering [article]

Bradley A. Chase
2009 arXiv   pre-print
Chapter 4 studies the problem of quantum parameter estimation and introduces the quantum particle filter as a practical computational method for parameter estimation via continuous measurement.  ...  Chapters 2 and 3 provide a review of classical and quantum probability theory, stochastic calculus and filtering.  ...  Consider the probability space for throwing two coins, given by Ω = {HH, T T, HT, T H} with F and P defined but unimportant for this example.  ... 
arXiv:0908.1200v1 fatcat:72mxz72q6feopjnreekaphiype

Bio-inspired cost-aware optimization for data-intensive service provision

Lijuan Wang, Jun Shen, Junzhou Luo
2015 Concurrency and Computation  
Scientists and computer engineers have coined a new term for this phenomenon: “Big Data”.  ...  Near Parameter Free Ant Colony Optimisation. In Ant Colony Optimization and Swarm Intelligence, M. Dorigo, M. Birattari, C. Blum, L. Gambardella, F. Mondada, and T. Stützle, Eds.  ... 
doi:10.1002/cpe.3589 fatcat:ac3v652klncdndi6bkglyxe5v4

Continuous Measurement and Stochastic Methods in Quantum Optical Systems [article]

Robert L. Cook
2013 arXiv   pre-print
Our model predicts that for a probe in the near infrared, noncommuting measurement effects are apparent for subpicosecond times.  ...  Here we explore the fundamental limits of this protocol by studying an idealized model for pure qubits, which is limited only by measurement backaction.  ...  Placing a $50 bet that a coin toss will land heads is an example of a random variable. Another example of a random variable the indicator function χ A (ω) for any event A ∈ F.  ... 
arXiv:1301.6193v1 fatcat:k7p4lbcvbffljceokxjdagfvsu

The artificial epigenetic network

Alexander P. Turner, Michael A. Lones, Luis A. Fuente, Susan Stepney, Leo S. D. Caves, Andy Tyrrell
2013 2013 IEEE International Conference on Evolvable Systems (ICES)  
Hence, the artificial epigenetic network can contain many different regulatory circuits, each with specific properties.  ...  An emergent property is that the epigenetic structures can partition the network into functional units corresponding to the logical decomposition of the tasks, and control these units with a switch like  ...  Vanessa for the adventures throughout my time in York; Ben and Andy M for being both hilarious people and great friends; Chris W for his inspiration; Chris A for always welcoming me back to my homeland  ... 
doi:10.1109/ices.2013.6613284 dblp:conf/ices/TurnerLFSCT13 fatcat:sr6dssfn6naoddlelnvzbdlvpe
« Previous Showing results 1 — 15 out of 93 results