English
Related papers

Related papers: Falsification and future performance

200 papers

Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Haoxuan Qu , Yanchao Li , Lin Geng Foo , Jason Kuen , Jiuxiang Gu , Jun Liu

Real-world offline datasets are often subject to data corruptions (such as noise or adversarial attacks) due to sensor failures or malicious attacks. Despite advances in robust offline reinforcement learning (RL), existing methods struggle…

Machine Learning · Computer Science 2024-11-04 Rui Yang , Jie Wang , Guoping Wu , Bin Li

Inferring models, predicting the future, and estimating the entropy rate of discrete-time, discrete-event processes is well-worn ground. However, a much broader class of discrete-event processes operates in continuous-time. Here, we provide…

Statistical Mechanics · Physics 2020-05-11 S. E. Marzen , J. P. Crutchfield

We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves…

Machine Learning · Computer Science 2021-02-08 William F. Whitney , Min Jae Song , David Brandfonbrener , Jaan Altosaar , Kyunghyun Cho

Strategic classification studies learning settings in which individuals can modify their features, at a cost, in order to influence the classifier's decision. A central question is how the sample complexity of the induced (strategic)…

Machine Learning · Computer Science 2026-05-15 Yuval Filmus , Shay Moran , Elizaveta Nesterova , Nir Rosenfeld , Alexander Shlimovich

Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a…

Machine Learning · Computer Science 2025-02-18 Alvaro H. C. Correia , Fabio Valerio Massoli , Christos Louizos , Arash Behboodi

Formalising the confrontation of opinions (models) to observations (data) is the task of Inferential Statistics. Information Theory provides us with a basic functional, the relative entropy (or Kullback-Leibler divergence), an asymmetrical…

Information Theory · Computer Science 2015-03-13 François Bavaud

Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency…

We consider the task of forecasting an infinite sequence of future observations based on some number of past observations, where the probability measure generating the observations is "suspected" to satisfy one or more of a set of…

Machine Learning · Computer Science 2019-05-17 Vanessa Kosoy

We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes. Existing algorithms…

Artificial Intelligence · Computer Science 2017-07-18 Yuxin Chen , Jean-Michel Renders , Morteza Haghir Chehreghani , Andreas Krause

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

Machine Learning · Computer Science 2022-08-16 Kenneth Bogert , Yikang Gui , Prashant Doshi

We find that models report highest confidence precisely when they are fabricating. Across four model families (OLMo-3, Llama-3.1, Qwen3, Mistral), self-reported confidence inversely correlates with accuracy, with AUC ranging from 0.28 to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Tony Mason , Vaastav Anand

The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration. Existing algorithms provide little information about the quality of their current policy before executing it, and thus have…

Machine Learning · Computer Science 2019-05-29 Christoph Dann , Lihong Li , Wei Wei , Emma Brunskill

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Machine Learning · Computer Science 2020-10-13 Pietro Buzzega , Matteo Boschini , Angelo Porrello , Simone Calderara

To quantify the complexity of a system, entropy-based methods have received considerable critical attentions in real-world data analysis. Among numerous entropy algorithms, amplitude-based formulas, represented by Sample Entropy, suffer…

Signal Processing · Electrical Eng. & Systems 2022-01-12 Hongjian Xiao , Danilo P. Mandic

The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as it has finite VC dimension. The improved sample complexity is…

Machine Learning · Computer Science 2026-01-26 Navid Ardeshir , Samuel Deng , Daniel Hsu , Jingwen Liu

The information diffusion prediction on social networks aims to predict future recipients of a message, with practical applications in marketing and social media. While different prediction models all claim to perform well, general…

Social and Information Networks · Computer Science 2025-01-16 Wenjin Xie , Xiaomeng Wang , Radosław Michalski , Tao Jia

Certified randomness guaranteed to be unpredictable by adversaries is central to information security. The fundamental randomness inherent in quantum physics makes certification possible from devices that are only weakly characterised, i.e.…

In this paper, we investigate the issue of error accumulation in critic networks updated via pessimistic temporal difference objectives. We show that the critic approximation error can be approximated via a recursive fixed-point model…

Machine Learning · Computer Science 2024-03-05 Michal Nauman , Mateusz Ostaszewski , Marek Cygan

We study a variant of Collaborative PAC Learning, in which we aim to learn an accurate classifier for each of the $n$ data distributions, while minimizing the number of samples drawn from them in total. Unlike in the usual collaborative…

Machine Learning · Computer Science 2024-05-24 Yuyang Deng , Mingda Qiao
‹ Prev 1 3 4 5 6 7 10 Next ›