English
Related papers

Related papers: The Limits of Inference Scaling Through Resampling

200 papers

Rejection sampling is a common tool for low dimensional problems ($d \leq 2$), often touted as an "easy" way to obtain valid samples from a distribution $f(\cdot)$ of interest. In practice it is non-trivial to apply, often requiring…

Computation · Statistics 2023-10-03 Edward Raff , Mark McLean , James Holt

Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and…

Artificial Intelligence · Computer Science 2026-03-20 Maksym Del , Markus Kängsepp , Marharyta Domnich , Ardi Tampuu , Lisa Yankovskaya , Meelis Kull , Mark Fishel

Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which…

Computation and Language · Computer Science 2024-10-31 Kexun Zhang , Shang Zhou , Danqing Wang , William Yang Wang , Lei Li

Hypothesis tests calibrated by (re)sampling methods (such as permutation, rank and bootstrap tests) are useful tools for statistical analysis, at the computational cost of requiring Monte-Carlo sampling for calibration. It is common and…

Methodology · Statistics 2024-09-30 Ivo V. Stoepker , Rui M. Castro

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples are surrounded by seen training samples in representation space. We find that a bound on empirical…

Machine Learning · Computer Science 2022-07-29 Xu Ji , Razvan Pascanu , Devon Hjelm , Balaji Lakshminarayanan , Andrea Vedaldi

Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence…

Machine Learning · Statistics 2014-06-20 Brian McWilliams , Gabriel Krummenacher , Mario Lucic , Joachim M. Buhmann

Several new methods have been proposed for performing valid inference after model selection. An older method is sampling splitting: use part of the data for model selection and part for inference. In this paper we revisit sample splitting…

Statistics Theory · Mathematics 2018-04-04 Alessandro Rinaldo , Larry Wasserman , Max G'Sell , Jing Lei

Large-scale industrial recommendation models predict the most relevant items from catalogs containing millions or billions of options. To train these models efficiently, a small set of irrelevant items (negative samples) is selected from…

Information Retrieval · Computer Science 2024-10-30 Arushi Prakash , Dimitrios Bermperidis , Srivas Chennu

For classification problems with significant class imbalance, subsampling can reduce computational costs at the price of inflated variance in estimating model parameters. We propose a method for subsampling efficiently for logistic…

Computation · Statistics 2014-09-24 William Fithian , Trevor Hastie

Despite the impressive generalization capabilities of deep neural networks, they have been repeatedly shown to be overconfident when they are wrong. Fixing this issue is known as model calibration, and has consequently received much…

Machine Learning · Computer Science 2024-02-15 Muthu Chidambaram , Rong Ge

Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…

Artificial Intelligence · Computer Science 2026-02-13 Xinhai Sun

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class…

Computer Vision and Pattern Recognition · Computer Science 2023-04-28 Maan Qraitem , Kate Saenko , Bryan A. Plummer

Sequential importance sampling algorithms have been defined to estimate likelihoods in models of ancestral population processes. However, these algorithms are based on features of the models with constant population size, and become…

Statistics Theory · Mathematics 2016-03-24 Coralie Merle , Raphaël Leblois , François Rousset , Pierre Pudlo

Understanding the impact of the most effective policies or treatments on a response variable of interest is desirable in many empirical works in economics, statistics and other disciplines. Due to the widespread winner's curse phenomenon,…

Methodology · Statistics 2022-10-25 Waverly Wei , Yuqing Zhou , Zeyu Zheng , Jingshen Wang

The objective of Bayesian inference is often to infer, from data, a probability measure for a random variable that can be used as input for Monte Carlo simulation. When datasets for Bayesian inference are small, a principle challenge is…

Computation · Statistics 2018-03-29 Jiaxin Zhang , Michael D. Shields

When many (m) null hypotheses are tested with a single dataset, the control of the number of false rejections is often the principal consideration. Two popular controlling rates are the probability of making at least one false discovery…

Methodology · Statistics 2013-07-11 Djalel Eddine Meskaldji , Jean-Philippe Thiran , Stephan Morgenthaler

For randomized controlled trials to be conclusive, it is important to set the target sample size accurately at the design stage. Comparing two normal populations, the sample size calculation requires specification of the variance other than…

Methodology · Statistics 2026-02-04 Hirotada Maeda , Satoshi Hattori , Tim Friede

When dealing with difficult inverse problems such as inverse rendering, using Monte Carlo estimated gradients to optimise parameters can slow down convergence due to variance. Averaging many gradient samples in each iteration reduces this…

Graphics · Computer Science 2023-09-28 Martin Balint , Karol Myszkowski , Hans-Peter Seidel , Gurprit Singh

Machine learning methods are increasingly applied in medical imaging, yet many reported improvements lack statistical robustness: recent works have highlighted that small but significant performance gains are highly likely to be false…

Machine Learning · Computer Science 2025-11-05 Thomas Sanchez , Pedro M. Gordaliza , Meritxell Bach Cuadra

While a broad range of techniques have been proposed to tackle distribution shift, the simple baseline of training on an $\textit{undersampled}$ balanced dataset often achieves close to state-of-the-art-accuracy across several popular…

Machine Learning · Computer Science 2023-06-21 Niladri S. Chatterji , Saminul Haque , Tatsunori Hashimoto
‹ Prev 1 4 5 6 7 8 10 Next ›