English
Related papers

Related papers: An Axiomatic Approach to Loss Aggregation and an A…

200 papers

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit…

Computation and Language · Computer Science 2025-06-03 Junjie Zhang , Rushuai Yang , Shunyu Liu , Ting-En Lin , Fei Huang , Yi Chen , Yongbin Li , Dacheng Tao

This paper investigates the convergence properties of sample-average approximations (SAA) for set-valued systemic risk measures. We assume that the systemic risk measure is defined using a general aggregation function with some continuity…

Risk Management · Quantitative Finance 2024-08-19 Wissam AlAli , Çağın Ararat

Bayesian methods are often optimal, yet increasing pressure for fast computations, especially with streaming data, brings renewed interest in faster, possibly sub-optimal, solutions. The extent to which these algorithms approximate Bayesian…

Statistics Theory · Mathematics 2026-02-18 Sandra Fortini , Sonia Petrone

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Machine Learning · Statistics 2025-09-30 Wenhui Li , Shijin Gong , Xinyu Zhang

Collaborative learning in peer-to-peer networks offers the benefits of distributed learning while mitigating the risks associated with single points of failure inherent in centralized servers. However, adversarial workers pose potential…

Machine Learning · Computer Science 2025-01-09 Chandreyee Bhowmick , Xenofon Koutsoukos

We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the conventional learning-to-learn framework and the modern…

Machine Learning · Computer Science 2021-12-13 Qi Chen , Changjian Shui , Mario Marchand

We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper…

Machine Learning · Computer Science 2023-02-02 Changlong Wu , Mohsen Heidari , Ananth Grama , Wojciech Szpankowski

For each of $T$ time steps, $m$ experts report probability distributions over $n$ outcomes; we wish to learn to aggregate these forecasts in a way that attains a no-regret guarantee. We focus on the fundamental and practical aggregation…

Machine Learning · Computer Science 2023-10-11 Eric Neyman , Tim Roughgarden

Statistical inference can be seen as information processing involving input information and output information that updates belief about some unknown parameters. We consider the Bayesian framework for making inferences about dynamical…

Statistics Theory · Mathematics 2022-01-17 Artur O. Lopes , Silvia R. C. Lopes , Paulo Varandas

Supervised learning requires the specification of a loss function to minimise. While the theory of admissible losses from both a computational and statistical perspective is well-developed, these offer a panoply of different choices. In…

Machine Learning · Computer Science 2020-02-11 Richard Nock , Aditya Krishna Menon

Offline reinforcement learning aims to learn an agent from pre-collected datasets, avoiding unsafe and inefficient real-time interaction. However, inevitable access to out-ofdistribution actions during the learning process introduces…

Artificial Intelligence · Computer Science 2026-03-06 Fan Zhang , Baoru Huang , Xin Zhang

A common but rarely examined assumption in machine learning is that training yields models that actually satisfy their specified objective function. We call this the Objective Satisfaction Assumption (OSA). Although deviations from OSA are…

Artificial Intelligence · Computer Science 2026-02-11 Antoine Maier , Aude Maier , Tom David

Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we propose a theory based on generalization bounds that…

Machine Learning · Statistics 2024-05-16 Daniel Csillag , Claudio José Struchiner , Guilherme Tegoni Goedert

Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks, we analyze gradient-based descent algorithms for boosting…

Machine Learning · Computer Science 2012-02-15 Alexander Grubb , J. Andrew Bagnell

Generalized additive models (GAMs) provide a way to blend parametric and non-parametric (function approximation) techniques together, making them flexible tools suitable for many modeling problems. For instance, GAMs can be used to…

Methodology · Statistics 2023-03-07 Antti Solonen , Stratos Staboulis

This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Jayateja Kalla , Soma Biswas

We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation…

Machine Learning · Statistics 2019-10-14 Pierre Alquier , The Tien Mai , Massimiliano Pontil

Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly…

Machine Learning · Computer Science 2024-01-08 Firas Laakom , Yuheng Bu , Moncef Gabbouj

An algorithm is proposed for solving optimization problems arising in neural network training for supervised learning. The unique feature of the algorithm is the use of an auxiliary loss, in addition to the original loss employed for model…

Optimization and Control · Mathematics 2026-05-11 Yunlang Zhu , Lingjun Guo , Zahra Khatti , Xiaoyi Qu , Chia-Yuan Wu , Lara Zebiane , Frank E. Curtis

We consider the task of aggregating beliefs of severalexperts. We assume that these beliefs are represented as probabilitydistributions. We argue that the evaluation of any aggregationtechnique depends on the semantic context of this task.…

Artificial Intelligence · Computer Science 2013-01-14 Pedrito Maynard-Reid , Urszula Chajewska