English
Related papers

Related papers: Prompts Generalize with Low Data: Non-vacuous Gene…

200 papers

Identifying optimal values for a high-dimensional set of hyperparameters is a problem that has received growing attention given its importance to large-scale machine learning applications such as neural architecture search. Recently…

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Computation and Language · Computer Science 2023-09-12 Max Marion , Ahmet Üstün , Luiza Pozzobon , Alex Wang , Marzieh Fadaee , Sara Hooker

Existing guarantees in terms of rigorous upper bounds on the generalization error for the original random forest algorithm, one of the most frequently used machine learning methods, are unsatisfying. We discuss and evaluate various…

Machine Learning · Computer Science 2019-03-07 Stephan Sloth Lorenzen , Christian Igel , Yevgeny Seldin

Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this observation, and…

Computation and Language · Computer Science 2024-06-18 Bangzheng Li , Ben Zhou , Xingyu Fu , Fei Wang , Dan Roth , Muhao Chen

Gaussian Processes (GPs) are a generic modelling tool for supervised learning. While they have been successfully applied on large datasets, their use in safety-critical applications is hindered by the lack of good performance guarantees. To…

Machine Learning · Statistics 2019-08-27 David Reeb , Andreas Doerr , Sebastian Gerwinn , Barbara Rakitsch

In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds, as other forms of capacity measures or regularizations are…

Machine Learning · Statistics 2024-02-22 Paul Viallard , Rémi Emonet , Amaury Habrard , Emilie Morvant , Valentina Zantedeschi

Uncertainty quantification requires efficient summarization of high- or even infinite-dimensional (i.e., non-parametric) distributions based on, e.g., suitable point estimates (modes) for posterior distributions arising from model-specific…

Statistics Theory · Mathematics 2024-04-10 Christian Clason , Tapio Helin , Remo Kretschmann , Petteri Piiroinen

We study Bayesian inference in statistical linear inverse problems with Gaussian noise and priors in Hilbert space. We focus our interest on the posterior contraction rate in the small noise limit. Existing results suffer from a certain…

Statistics Theory · Mathematics 2014-09-24 Sergios Agapiou , Peter Mathé

This paper draws on diverse areas of computer science to develop a unified view of computation: (1) Optimization in operations research, where a numerical objective function is maximized under constraints, is generalized from the numerical…

Artificial Intelligence · Computer Science 2013-02-11 A. Nait Abdallah , M. H. van Emden

Optimization problems with uncertain black-box constraints, modeled by warped Gaussian processes, have recently been considered in the Bayesian optimization setting. This work introduces a new class of constraints in which the same…

Optimization and Control · Mathematics 2020-06-16 Johannes Wiebe , Inês Cecílio , Jonathan Dunlop , Ruth Misener

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an auxiliary process reward model (PRM) is used to score and…

Machine Learning · Computer Science 2025-05-26 Zeen Song , Wenwen Qiang , Siyu Zhao , Changwen Zheng , Gang Hua

Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraints. We propose a…

Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons. To address this issue, recent bias mitigation methods for VQA…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Robik Shrestha , Kushal Kafle , Christopher Kanan

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

Computation and Language · Computer Science 2022-04-27 Navid Rezaei , Marek Z. Reformat

We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties. While our approach holds for arbitrary distributions, we instantiate it with Dirichlet distributions:…

Machine Learning · Computer Science 2021-10-20 Valentina Zantedeschi , Paul Viallard , Emilie Morvant , Rémi Emonet , Amaury Habrard , Pascal Germain , Benjamin Guedj

Why do larger language models generalize better? To investigate this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the compute-optimal regime, as described by the Chinchilla…

Machine Learning · Computer Science 2025-04-22 Marc Finzi , Sanyam Kapoor , Diego Granziol , Anming Gu , Christopher De Sa , J. Zico Kolter , Andrew Gordon Wilson

Quality pretraining data is often seen as the key to high-performance language models. However, progress in understanding pretraining data has been slow due to the costly pretraining runs required for data selection experiments. We present…

Computation and Language · Computer Science 2025-03-11 Tristan Thrush , Christopher Potts , Tatsunori Hashimoto

Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the oblivion and rote memorization problems in learning may…

Computation and Language · Computer Science 2023-09-20 Xiang Chen , Lei Li , Ningyu Zhang , Xiaozhuan Liang , Shumin Deng , Chuanqi Tan , Fei Huang , Luo Si , Huajun Chen

A learning method is self-certified if it uses all available data to simultaneously learn a predictor and certify its quality with a tight statistical certificate that is valid on unseen data. Recent work has shown that neural network…

Machine Learning · Computer Science 2021-12-13 Maria Perez-Ortiz , Omar Rivasplata , Emilio Parrado-Hernandez , Benjamin Guedj , John Shawe-Taylor

Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing that while LLMs can often infer unspecified requirements by default (41.1%), such behavior…

Computation and Language · Computer Science 2026-04-28 Chenyang Yang , Yike Shi , Qianou Ma , Michael Xieyang Liu , Christian Kästner , Tongshuang Wu
‹ Prev 1 4 5 6 7 8 10 Next ›