paper-with-me

Papers

Debiased Distribution Compression

2024-04-18 · Lingxiao Li, Raaz Dwivedi, Lester Mackey

Modern compression methods can summarize a target distribution $\mathbb{P}$ more succinctly than i.i.d. sampling but require access to a low-bias input sequence like a Markov chain converging quickly to $\mathbb{P}$. We introduce a new suite of compression methods suitable for compression with biased input sequences. Given $n$ points targeting the wrong distribution and quadratic time, Stein kernel thinning (SKT) returns $\sqrt{n}$ equal-weighted points with $\widetilde{O}(n^{-1/2})$ maximum mean discrepancy (MMD) to $\mathbb{P}$. For larger-scale compression tasks, low-rank SKT achieves the same feat in sub-quadratic time using an adaptive low-rank debiasing procedure that may be of independent interest. For downstream tasks that support simplex or constant-preserving weights, Stein recombination and Stein Cholesky achieve even greater parsimony, matching the guarantees of SKT with as few as $\text{poly-log}(n)$ weighted points. Underlying these advances are new guarantees for the quality of simplex-weighted coresets, the spectral decay of kernel matrices, and the covering numbers of Stein kernel Hilbert spaces. In our experiments, our techniques provide succinct and accurate posterior summaries while overcoming biases due to burn-in, approximate Markov chain Monte Carlo, and tempering.

📄 PDF Abstract BibTeX arXiv:2404.12290

Code (1)

microsoft/goodpoints 공식 구현 jax

Similar Papers 제목 키워드 기반

Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering

2022-10-26 · Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu 외

Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets

2022-03-24 · ACL 2022 5 · Yuxiang Wu, Matt Gardner, Pontus Stenetorp, Pradeep Dasigi

Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they are trained on, while not generalising to…

Natural Language Inference

Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they are trained on, while not generalising to…

Natural Language Inference

Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective

2024-09-26 · Yu Wang, Yuxuan Yin, Peng Li

Semi-supervised learning (SSL) commonly exhibits confirmation bias, where models disproportionately favor certain classes, leading to errors in predicted pseudo labels that accumulate under a self-training paradigm. Unli…

image-classificationImage Classification

Policy Learning with $α$-Expected Welfare

2025-05-01 · Yanqin Fan, Yuan Qi, Gaoqian Xu

This paper proposes an optimal policy that targets the average welfare of the worst-off $\alpha$-fraction of the post-treatment outcome distribution. We refer to this policy as the $\alpha$-Expected Welfare Maximization …

valid