English
Related papers

Related papers: A note on the impossibility of conditional PAC-eff…

200 papers

Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. However, excessive reliance on chain-of-thought (CoT) reasoning…

Computation and Language · Computer Science 2025-05-22 Jinghui Lu , Haiyang Yu , Siliang Xu , Shiwei Ran , Guozhi Tang , Siqi Wang , Bin Shan , Teng Fu , Hao Feng , Jingqun Tang , Han Wang , Can Huang

Obtaining a non-parametric expression for an interventional distribution is one of the most fundamental tasks in causal inference. Such an expression can be obtained for an identifiable causal effect by an algorithm or by manual application…

Machine Learning · Statistics 2018-06-20 Santtu Tikka , Juha Karvanen

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…

Computation and Language · Computer Science 2026-02-24 Siran Liu , Cyril Y. He

We revisit the fundamental question of simple-versus-simple hypothesis testing with an eye towards computational complexity, as the statistically optimal likelihood ratio test is often computationally intractable in high-dimensional…

Statistics Theory · Mathematics 2025-05-05 Ankur Moitra , Alexander S. Wein

One method for obtaining generalizable solutions to machine learning tasks when presented with diverse training environments is to find \textit{invariant representations} of the data. These are representations of the covariates such that…

Machine Learning · Computer Science 2022-08-16 Advait Parulekar , Karthikeyan Shanmugam , Sanjay Shakkottai

The field of distribution-free predictive inference provides tools for provably valid prediction without any assumptions on the distribution of the data, which can be paired with any regression algorithm to provide accurate and reliable…

Statistics Theory · Mathematics 2023-01-19 Michael Bian , Rina Foygel Barber

We propose a novel approach to understanding the decision making of complex machine learning models (e.g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference methodology called…

Artificial Intelligence · Computer Science 2020-09-21 Daniel Neider , Bishwamittra Ghosh

This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. Given inputs, PCP construct the predictive set based on random samples from…

Machine Learning · Statistics 2022-06-22 Zhendong Wang , Ruijiang Gao , Mingzhang Yin , Mingyuan Zhou , David M. Blei

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

Machine Learning · Computer Science 2024-04-22 Diego Calanzone , Stefano Teso , Antonio Vergari

We consider variable selection in high-dimensional linear models where the number of covariates greatly exceeds the sample size. We introduce the new concept of partial faithfulness and use it to infer associations between the covariates…

Methodology · Statistics 2012-01-12 Peter Bühlmann , Markus Kalisch , Marloes H. Maathuis

An automated explanation facility for Bayesian conditioning aimed at improving user acceptance of probability-based decision support systems has been developed. The domain-independent facility is based on an information processing…

Artificial Intelligence · Computer Science 2013-04-11 Christopher Elsaesser

Increasing amounts of available data have led to a heightened need for representing large-scale probabilistic knowledge bases. One approach is to use a probabilistic database, a model with strong assumptions that allow for efficiently…

Artificial Intelligence · Computer Science 2019-04-04 Tal Friedman , Guy Van den Broeck

Despite the theoretical significance and wide practical use of regular expressions, the computational complexity of learning them has been largely unexplored. We study the computational hardness of improperly learning regular expressions in…

Machine Learning · Computer Science 2025-10-07 Idan Attias , Lev Reyzin , Nathan Srebro , Gal Vardi

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman

We consider a monopolist seller facing a single buyer with additive valuations over n heterogeneous, independent items. It is known that in this important setting optimal mechanisms may require randomization [HR12], use menus of infinite…

Computer Science and Game Theory · Computer Science 2015-11-17 Aviad Rubinstein

This paper explores the space of (propositional) probabilistic logical languages, ranging from a purely `qualitative' comparative language to a highly `quantitative' language involving arbitrary polynomials over probability terms. While…

Logic · Mathematics 2023-08-17 Duligur Ibeling , Thomas Icard , Krzysztof Mierzewski , Milan Mossé

The basic problem in the PAC model of computational learning theory is to determine which hypothesis classes are efficiently learnable. There is presently a dearth of results showing hardness of learning problems. Moreover, the existing…

Machine Learning · Computer Science 2014-03-11 Amit Daniely , Nati Linial , Shai Shalev-Shwartz

Conformal prediction methodology has recently been extended to the covariate shift setting, where the distribution of covariates differs between training and test data. While existing results ensure that the prediction sets from these…

Machine Learning · Statistics 2026-02-09 Mehrdad Pournaderi , Yu Xiang

We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee…

Machine Learning · Computer Science 2022-01-03 Jiafan He , Dongruo Zhou , Quanquan Gu

Limit-average automata are weighted automata on infinite words that use average to aggregate the weights seen in infinite runs. We study approximate learning problems for limit-average automata in two settings: passive and active. In the…

Formal Languages and Automata Theory · Computer Science 2019-06-27 Jakub Michaliszyn , Jan Otop