English
Related papers

Related papers: Correcting Stochastic Update Bias in Preconditione…

200 papers

Previous studies have established that language models manifest stereotyped biases. Existing debiasing strategies, such as retraining a model with counterfactual data, representation projection, and prompting often fail to efficiently…

Computation and Language · Computer Science 2025-03-12 Xin Xu , Wei Xu , Ningyu Zhang , Julian McAuley

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

Many core concepts in political science are latent and therefore can only be measured with error. Measurement error in a predictor attenuates slope coefficient estimates in regression, biasing them toward zero. We show that widely used…

Applications · Statistics 2026-02-04 Connor T. Jerzak , Stephen A. Jessee

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Computation and Language · Computer Science 2024-06-13 Chong Li , Shaonan Wang , Jiajun Zhang , Chengqing Zong

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…

Computation and Language · Computer Science 2026-04-21 Zhuo Chen , Yuxuan Miao , Supryadi , Deyi Xiong

Deep probabilistic time series forecasting has gained attention for its ability to provide nonlinear approximation and valuable uncertainty quantification for decision-making. However, existing models often oversimplify the problem by…

Machine Learning · Statistics 2024-10-22 Vincent Zhihao Zheng , Seongjin Choi , Lijun Sun

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

Machine Learning · Computer Science 2024-06-06 Ionut-Vlad Modoranu , Aleksei Kalinov , Eldar Kurtic , Elias Frantar , Dan Alistarh

We introduce novel variants of momentum by incorporating the variance of the stochastic loss function. The variance characterizes the confidence or uncertainty of the local features of the averaged loss surface across the i.i.d. subsets of…

Machine Learning · Computer Science 2019-05-31 Vineeth S. Bhaskara , Sneha Desai

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Computer Vision and Pattern Recognition · Computer Science 2018-07-03 Lisa Anne Hendricks , Kaylee Burns , Kate Saenko , Trevor Darrell , Anna Rohrbach

Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optimizer steps for a proportional increase in batch size. While…

Machine Learning · Computer Science 2025-12-17 Martin Marek , Sanae Lotfi , Aditya Somasundaram , Andrew Gordon Wilson , Micah Goldblum

Covariate adjustment is an approach to improve the precision of trial analyses by adjusting for baseline variables that are prognostic of the primary endpoint. Motivated by the SEARCH Universal HIV Test-and-Treat Trial (2013-2017), we tell…

Methodology · Statistics 2025-12-16 Laura B. Balzer , Mark J. van der Laan , Maya L. Petersen

Current deep learning adaptive optimizer methods adjust the step magnitude of parameter updates by altering the effective learning rate used by each parameter. Motivated by the known inverse relation between batch size and learning rate on…

Machine Learning · Computer Science 2022-08-02 Cristian Simionescu , George Stoica , Robert Herscovici

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" through a series of…

Machine Learning · Computer Science 2025-06-17 Teodora Srećković , Jonas Geiping , Antonio Orvieto

Preconditioning has long been a staple technique in optimization, often applied to reduce the condition number of a matrix and speed up the convergence of algorithms. Although there are many popular preconditioning techniques in practice,…

Optimization and Control · Mathematics 2022-11-08 Zhaonan Qu , Wenzhi Gao , Oliver Hinder , Yinyu Ye , Zhengyuan Zhou

Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…

Computer Vision and Pattern Recognition · Computer Science 2019-07-15 Kirthi Shankar Sivamani

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Computation and Language · Computer Science 2013-03-22 Damianos Karakos , Mark Dredze , Sanjeev Khudanpur

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method…

Computation and Language · Computer Science 2021-01-26 Masahiro Kaneko , Danushka Bollegala

This paper delves into the continuous post-training optimization methods for small language models, and proposes a continuous post-training alignment data construction method for small language models. The core of this method is based on…

Computation and Language · Computer Science 2024-12-24 Keke Zhai

Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Laura Cabello , Emanuele Bugliarello , Stephanie Brandl , Desmond Elliott

In this experimental work, we present a general framework based on the Bregman log determinant divergence for preconditioning Hermitian positive definite linear systems. We explore this divergence as a measure of discrepancy between a…

Numerical Analysis · Mathematics 2024-10-10 Andreas A. Bock , Martin S. Andersen