English
Related papers

Related papers: Fully lifted random duality theory

200 papers

In some practical learning tasks, such as traffic video analysis, the number of available training samples is restricted by different factors, such as limited communication bandwidth and computation power. Determinantal Point Process (DPP)…

Machine Learning · Computer Science 2023-08-17 Xiwen Chen , Huayu Li , Rahul Amin , Abolfazl Razi

Applications of Reinforcement Learning (RL), in which agents learn to make a sequence of decisions despite lacking complete information about the latent states of the controlled system, that is, they act under partial observability of the…

Machine Learning · Computer Science 2022-05-26 Qinghua Liu , Alan Chung , Csaba Szepesvári , Chi Jin

Deep learning (DL) can automatically construct intelligent agents, deep neural networks (alternatively, DL models), that can outperform humans in certain tasks. However, the operating principles of DL remain poorly understood, making its…

Machine Learning · Computer Science 2025-05-20 Jung Hoon Lee , Sujith Vijayan

Integrating data from multiple sources expands research opportunities at low cost. However, due to different data collection processes and privacy constraints, unique identifiers are unavailable. Record Linkage (RL) algorithms address this…

Methodology · Statistics 2025-10-07 Kayané Robach , Michel H. Hof , Mark A. van de Wiel

Data exhibiting heavy-tails in one or more dimensions is often studied using the framework of regular variation. In a multivariate setting this requires identifying specific forms of dependence in the data; this means identifying that the…

Statistics Theory · Mathematics 2017-02-02 Bikramjit Das , Sidney I. Resnick

Online decision tree learning algorithms typically examine all features of a new data point to update model parameters. We propose a novel alternative, Reinforcement Learning- based Decision Trees (RLDT), that uses Reinforcement Learning…

Machine Learning · Computer Science 2015-07-27 Abhinav Garlapati , Aditi Raghunathan , Vaishnavh Nagarajan , Balaraman Ravindran

Deep neural networks (DNNs) exhibit crackling-like avalanches whose origin lacks a mechanistic explanation. Here, I derive a stochastic theory of deep information propagation (DIP) by incorporating Central Limit Theorem (CLT)-level…

Disordered Systems and Neural Networks · Physics 2025-12-02 Arsham Ghavasieh

We develop a method to solve, theoretically and numerically, general optimal stopping problems. Our general setting allows for multiple exercise rights, i.e., optimal multiple stopping, for a robust evaluation that accounts for model…

In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…

Machine Learning · Computer Science 2022-01-03 Mastane Achab , Gergely Neu

In reinforcement learning (RL), the consideration of multivariate reward signals has led to fundamental advancements in multi-objective decision-making, transfer learning, and representation learning. This work introduces the first…

Machine Learning · Computer Science 2024-09-05 Harley Wiltzer , Jesse Farebrother , Arthur Gretton , Mark Rowland

A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and…

Machine Learning · Computer Science 2021-10-22 Yuanhao Wang , Ruosong Wang , Sham M. Kakade

In recent years, two prominent paradigms have shaped distributionally robust optimization (DRO), modeling distributional ambiguity through $\phi$-divergences and Wasserstein distances, respectively. While the former focuses on ambiguity in…

Optimization and Control · Mathematics 2025-12-22 Jose Blanchet , Daniel Kuhn , Jiajin Li , Bahar Taskesen

While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient…

Machine Learning · Computer Science 2026-03-23 Yikun Wang , Yang Li , Yik-Chung Wu , Rui Zhang

A fruitful way of obtaining meaningful, possibly concrete, algorithmically random numbers is to consider a potential behaviour of a Turing machine and its probability with respect to a measure (or semi-measure) on the input space of binary…

Computational Complexity · Computer Science 2017-06-13 George Barmpalias , Douglas Cenzer , Christopher P. Porter

When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In turn, their performance is inconsistent and often poor. Whether the performance of distributional…

Machine Learning · Computer Science 2024-10-16 Harley Wiltzer , Marc G. Bellemare , David Meger , Patrick Shafto , Yash Jhaveri

Bandit and reinforcement learning (RL) problems can often be framed as optimization problems where the goal is to maximize average performance while having access only to stochastic estimates of the true gradient. Traditionally, stochastic…

Machine Learning · Computer Science 2021-02-22 Wesley Chung , Valentin Thomas , Marlos C. Machado , Nicolas Le Roux

The conventional duality analysis is employed to identify a location of a critical point on a uniform lattice without any disorder in its structure. In the present study, we deal with the random planar lattice, which consists of the…

Disordered Systems and Neural Networks · Physics 2015-06-11 Masayuki Ohzeki , Keisuke Fujii

The doubly-robust (DR) estimator is popular for evaluating causal effects in observational studies and is often perceived as more desirable than inverse probability weighting (IPW) or outcome modeling alone because it provides extra…

Methodology · Statistics 2026-02-03 Chengxin Yang , Laine E. Thomas , Fan Li

Interpretability of AI models allows for user safety checks to build trust in these models. In particular, decision trees (DTs) provide a global view on the learned model and clearly outlines the role of the features that are critical to…

Machine Learning · Computer Science 2023-04-13 Hector Kohler , Riad Akrour , Philippe Preux

We consider the injectivity property of the ReLU networks layers. Determining the ReLU injectivity capacity (ratio of the number of layer's inputs and outputs) is established as isomorphic to determining the capacity of the so-called…

Machine Learning · Statistics 2024-10-29 Mihailo Stojnic