English
Related papers

Related papers: Robust Comparative Statics with Misspecified Bayes…

200 papers

We revisit a model proposed by Freedman etal in \cite{freedman} which describes the dynamics of a population diffusing in a patchy environment. From their work it is known that positive steady states exist for this model, but not whether…

Dynamical Systems · Mathematics 2025-05-08 Patrick de Leenheer , Jane Shaw MacDonald , Swati Patel

Stochastic resetting and noise-enhanced stability are two phenomena which can affect the lifetime and relaxation of nonequilibrium states. They can be considered as measures of controlling the efficiency of the completion process when a…

Statistical Mechanics · Physics 2022-06-22 Karol Capała , Bartłomiej Dybiec , Ewa Gudowska-Nowak

This paper proves that the episodic learning environment of every finite-horizon decision task has a unique steady state under any behavior policy, and that the marginal distribution of the agent's input indeed converges to the steady-state…

Machine Learning · Computer Science 2021-01-14 Huang Bojun

Properties of stochastic systems are defined by the noise type and deterministic forces acting on the system. In out-of-equilibrium setups, e.g., for motions under action of L\'evy noises, the existence of the stationary state is not only…

Statistical Mechanics · Physics 2023-06-21 Przemysław Pogorzelec , Bartłomiej Dybiec

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to differences in observation space and…

Machine Learning · Computer Science 2025-04-03 Nicolas Espinosa-Dice , Sanjiban Choudhury , Wen Sun , Gokul Swamy

We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…

Machine Learning · Computer Science 2024-03-15 Vladimir R. Kostic , Pietro Novelli , Riccardo Grazzi , Karim Lounici , Massimiliano Pontil

Monotone learning describes learning processes in which expected performance consistently improves as the amount of training data increases. However, recent studies challenge this conventional wisdom, revealing significant gaps in the…

Machine Learning · Computer Science 2025-05-22 Ming Li , Chenyi Zhang , Qin Li

A pervasive phenomenon in machine learning applications is distribution shift, where training and deployment conditions for a machine learning model differ. As distribution shift typically results in a degradation in performance, much…

Machine Learning · Statistics 2024-01-23 Philip Amortila , Tongyi Cao , Akshay Krishnamurthy

Stochastic resetting has been a subject of considerable interest within statistical physics, both as means of improving completion times of complex processes such as searches and as a paradigm for generating nonequilibrium stationary…

Statistical Mechanics · Physics 2025-04-09 Martin R. Evans , John C. Sunil

Surprise-based learning allows agents to rapidly adapt to non-stationary stochastic environments characterized by sudden changes. We show that exact Bayesian inference in a hierarchical model gives rise to a surprise-modulated trade-off…

Machine Learning · Statistics 2020-09-25 Vasiliki Liakoni , Alireza Modirshanechi , Wulfram Gerstner , Johanni Brea

Reliable optimal control is challenging when the dynamics of a nonlinear system are unknown and only infrequent, noisy output measurements are available. This work addresses this setting of limited sensing by formulating a Bayesian prior…

Systems and Control · Electrical Eng. & Systems 2026-05-21 Robert Lefringhausen , Theodor Springer , Sandra Hirche

The utilization of online stochastic algorithms is popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches. When a constant step-size is used,…

Optimization and Control · Mathematics 2023-07-19 Stefan Vlaski , Elsa Rizk , Ali H. Sayed

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

Machine Learning · Computer Science 2024-04-03 Chenjia Bai , Peng Liu , Kaiyu Liu , Lingxiao Wang , Yingnan Zhao , Lei Han

This paper investigates the asymptotic behavior of stochastic recursive inclusions in the presence of non-zero, non-diminishing bias, a setting that frequently arises in zeroth-order optimization, stochastic approximation with…

Optimization and Control · Mathematics 2026-01-19 Anik Kumar Paul , Karthik Shenoy , Arun D. Mahindrakar

We introduce the notion of regularized Bayesian best response (RBBR) learning dynamic in heterogeneous population games. We obtain such a dynamic via perturbation by an arbitrary lower semicontinuous, strongly convex regularizer in Bayesian…

Optimization and Control · Mathematics 2023-03-13 Sayan Mukherjee , Souvik Roy

Real-world applications of contextual bandits often exhibit non-stationarity due to seasonality, serendipity, and evolving social trends. While a number of non-stationary contextual bandit learning algorithms have been proposed in the…

Machine Learning · Computer Science 2023-10-17 Zheqing Zhu , Yueyang Liu , Xu Kuang , Benjamin Van Roy

We study optimal estimation when the likelihood may be misspecified. Building on tools from the theory of decision-making under uncertainty, we analyze a class of axiomatically grounded optimality criteria which nests several existing…

Econometrics · Economics 2026-04-28 Isaiah Andrews , Ricky Li , Yucheng Shang

In this paper, under an abstract setting we establish the spreading properties and the existence, non-existence and global attractivity of spatially heterogeneous steady states for a large class of monotone evolution systems without the…

Dynamical Systems · Mathematics 2025-10-22 Taishan Yi , Xiao-Qiang Zhao

Stochastic processes offer a fundamentally different paradigm of dynamics than deterministic processes, the most prominent example of the latter being Newton's laws of motion. Here, we discuss in a pedagogical manner a simple and…

Statistical Mechanics · Physics 2022-04-15 Shamik Gupta , Arun M. Jayannavar

This paper presents a new condition for the existence of optimal stationary policies in average-cost continuous-time Markov decision processes with unbounded cost and transition rates, arising from controlled queueing systems. This…

Optimization and Control · Mathematics 2015-04-23 Cao Ping , Xie Jingui