English
Related papers

Related papers: Take Goodhart Seriously: Principled Limit on Gener…

200 papers

During the past decades, numerous successes of AI has been made on "specific capabilities", named closed-world, such as artificial environments or specific real-world tasks. This well-defined narrow capability brings two nice benefits, a…

Machine Learning · Computer Science 2025-07-08 Jianyu Zhang

Virtually all machine learning tasks are characterized using some form of loss function, and "good performance" is typically stated in terms of a sufficiently small average loss, taken over the random draw of test data. While optimizing for…

Machine Learning · Statistics 2023-12-01 Matthew J. Holland , Kazuki Tanabe

We consider the approximation capability of orthogonal super greedy algorithms (OSGA) and its applications in supervised learning. OSGA is concerned with selecting more than one atoms in each iteration step, which, of course, greatly…

Machine Learning · Computer Science 2014-09-19 Jian Fang , Shaobo Lin , Zongben Xu

We explore in some detail the notion of algorithmic stability as a viable framework for analyzing the generalization error of learning algorithms. We introduce the new notion of training stability of a learning algorithm and show that, in a…

Machine Learning · Computer Science 2013-01-07 Samuel Kutin , Partha Niyogi

Learning-to-optimize leverages machine learning to accelerate optimization algorithms. While empirical results show tremendous improvements compared to classical optimization algorithms, theoretical guarantees are mostly lacking, such that…

Machine Learning · Computer Science 2025-06-02 Michael Sucker , Peter Ochs

The arrival of AI techniques in computations, with the potential for hallucinations and non-robustness, has made trustworthiness of algorithms a focal point. However, trustworthiness of the many classical approaches are not well understood.…

Optimization and Control · Mathematics 2023-12-19 Alexander Bastounis , Felipe Cucker , Anders C. Hansen

Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is…

Machine Learning · Computer Science 2018-11-22 Bryan Wilder , Bistra Dilkina , Milind Tambe

Machine learning algorithms are increasingly used to inform critical decisions. There is a growing concern about bias, that algorithms may produce uneven outcomes for individuals in different demographic groups. In this work, we measure…

Machine Learning · Computer Science 2021-06-01 Runshan Fu , Yangfan Liang , Peter Zhang

Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not…

Optimization and Control · Mathematics 2021-12-13 Yafei Wang , Bo Pan , Wei Tu , Peng Liu , Bei Jiang , Chao Gao , Wei Lu , Shangling Jui , Linglong Kong

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the…

Machine Learning · Computer Science 2020-12-23 Assaf Dauber , Meir Feder , Tomer Koren , Roi Livni

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the…

Machine Learning · Computer Science 2018-01-16 Ankit Pensia , Varun Jog , Po-Ling Loh

One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear regression. In many…

Machine Learning · Computer Science 2023-11-22 Jing Xu , Jiaye Teng , Yang Yuan , Andrew Chi-Chih Yao

The Artificial Intelligence field has focused on developing optimisation methods to solve multiple problems, specifically problems that we thought to be only solvable through cognition. The obtained results have been outstanding, being able…

Machine Learning · Computer Science 2025-07-08 Alfredo Ibias

Algorithmic stability is a classical approach to understanding and analysis of the generalization error of learning algorithms. A notable weakness of most stability-based generalization bounds is that they hold only in expectation.…

Machine Learning · Computer Science 2019-06-25 Vitaly Feldman , Jan Vondrak

Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this…

Artificial Intelligence · Computer Science 2025-01-06 Benjamin Roth , Pedro Henrique Luz de Araujo , Yuxi Xia , Saskia Kaltenbrunner , Christoph Korab

We study reinforcement learning from human feedback under misspecification. Sometimes human feedback is systematically wrong on certain types of inputs, like a broken compass that points the wrong way in specific regions. We prove that when…

Artificial Intelligence · Computer Science 2025-09-16 Madhava Gaikwad

Generalization error bounds are essential for comprehending how well machine learning models work. In this work, we suggest a novel method, i.e., the Auxiliary Distribution Method, that leads to new upper bounds on expected generalization…

Machine Learning · Computer Science 2024-04-18 Gholamali Aminian , Saeed Masiha , Laura Toni , Miguel R. D. Rodrigues

The AI-alignment problem arises when there is a discrepancy between the goals that a human designer specifies to an AI learner and a potential catastrophic outcome that does not reflect what the human designer really wants. We argue that a…

Machine Learning · Computer Science 2020-04-10 Shai Shalev-Shwartz , Shaked Shammah , Amnon Shashua

Fairness-aware machine learning (fair-ml) techniques are algorithmic interventions designed to ensure that individuals who are affected by the predictions of a machine learning model are treated fairly. The problem is often posed as an…

Machine Learning · Computer Science 2024-07-03 Hilde Weerts , Lambèr Royakkers , Mykola Pechenizkiy

Supervised learning has gone beyond the expected risk minimization framework. Central to most of these developments is the introduction of more general aggregation functions for losses incurred by the learner. In this paper, we turn towards…

Machine Learning · Computer Science 2024-06-05 Armando J. Cabrera Pacheco , Rabanus Derr , Robert C. Williamson