English
Related papers

Related papers: On overfitting and asymptotic bias in batch reinfo…

200 papers

It can be argued that optimal prediction should take into account all available data. Therefore, to evaluate a prediction interval's performance one should employ conditional coverage probability, conditioning on all available observations.…

Statistics Theory · Mathematics 2021-03-02 Yunyi Zhang , Dimitris N. Politis

During the last years, asymptotic (or sequential) constraint qualifications, which postulate upper semicontinuity of certain set-valued mappings and provide a natural companion of asymptotic stationarity conditions, have been shown to be…

Optimization and Control · Mathematics 2023-02-10 Matúš Benko , Patrick Mehlitz

Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long…

Machine Learning · Computer Science 2021-07-06 Nicolò Botteghi , Mannes Poel , Beril Sirmacek , Christoph Brune

Learning representations of data, and in particular learning features for a subsequent prediction task, has been a fruitful area of research delivering impressive empirical results in recent years. However, relatively little is understood…

Machine Learning · Computer Science 2016-11-11 Daniel McNamara , Cheng Soon Ong , Robert C. Williamson

Annotating datasets is one of the main costs in nowadays supervised learning. The goal of weak supervision is to enable models to learn using only forms of labelling which are cheaper to collect, as partial labelling. This is a type of…

Machine Learning · Computer Science 2021-02-02 Vivien Cabannes , Alessandro Rudi , Francis Bach

Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to…

Machine Learning · Computer Science 2026-05-22 David Perera , Victor Moura , Lais Isabelle Alves dos Santos , Michel F. C. Haddad , Flavio Figueiredo

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for…

Machine Learning · Computer Science 2019-02-18 Yuhui Wang , Hao He , Xiaoyang Tan

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining…

Artificial Intelligence · Computer Science 2017-09-13 Denis Steckelmacher , Diederik M. Roijers , Anna Harutyunyan , Peter Vrancx , Hélène Plisnier , Ann Nowé

The phenomenon of benign overfitting, where a predictor perfectly fits noisy training data while attaining near-optimal expected loss, has received much attention in recent years, but still remains not fully understood beyond well-specified…

Machine Learning · Computer Science 2023-04-18 Ohad Shamir

Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length…

Machine Learning · Computer Science 2025-09-16 Wuhao Wang , Zhiyong Chen

During probabilistic learning organisms often apply a sub-optimal "probability-matching" strategy, where selection rates match reward probabilities, rather than engaging in the optimal "maximization" strategy, where the option with the…

Neurons and Cognition · Quantitative Biology 2021-12-09 Liran Szlak , Kristoffer Aberg , Rony Paz

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

Machine Learning · Computer Science 2022-03-17 Cong Lu , Philip J. Ball , Jack Parker-Holder , Michael A. Osborne , Stephen J. Roberts

Modern machine learning classifiers often exhibit vanishing classification error on the training set. They achieve this by learning nonlinear representations of the inputs that maps the data into linearly separable classes. Motivated by…

Statistics Theory · Mathematics 2023-03-23 Andrea Montanari , Feng Ruan , Youngtak Sohn , Jun Yan

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a…

Computation and Language · Computer Science 2026-05-29 Xueqing Wu , Yu-Chi Lin , Kai-Wei Chang , Nanyun Peng

Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized…

Machine Learning · Computer Science 2019-06-07 Carles Gelada , Saurabh Kumar , Jacob Buckman , Ofir Nachum , Marc G. Bellemare

We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value…

Econometrics · Economics 2019-07-23 Mert Demirer , Vasilis Syrgkanis , Greg Lewis , Victor Chernozhukov

We consider an experiment with at least two stages or batches and $O(N)$ subjects per batch. First, we propose a semiparametric treatment effect estimator that efficiently pools information across the batches, and show it asymptotically…

Methodology · Statistics 2023-09-28 Harrison H. Li , Art B. Owen

Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not…

Machine Learning · Statistics 2020-12-11 Alejandro Cholaquidis , Ricardo Fraiman , Mariela Sued

We consider the development of adaptive, instance-dependent algorithms for interactive decision making (bandits, reinforcement learning, and beyond) that, rather than only performing well in the worst case, adapt to favorable properties of…

Machine Learning · Computer Science 2023-04-26 Andrew Wagenmaker , Dylan J. Foster
‹ Prev 1 3 4 5 6 7 10 Next ›