paper-with-me

Papers

A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models

2021-06-06 · NeurIPS 2021 12 · Ibrahim Alabdulmohsin, Mario Lucic

We present a scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes risk. We empirically validate its advantages on standard benchmark datasets across both classical algorithms as well as modern DNN architectures and demonstrate that it outperforms previous post-processing methods while performing on par with in-processing. In addition, we show that the proposed algorithm is particularly effective for models trained at scale where post-processing is a natural and practical choice.

📄 PDF Abstract BibTeX arXiv:2106.12887

Code (1)

google-research/google-research/tree/master/ml_debiaser 공식 구현 jax

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

A Near-Optimal Recipe for Debiasing Trained Machine Learning Models

2021-01-01 · Ibrahim Alabdulmohsin, Mario Lucic

We present an efficient and scalable algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes risk. Unlike previous black-box reductio…

BIG-bench Machine LearningClassificationGeneral Classification

Debiasing Word Embeddings Improves Multimodal Machine Translation

2019-05-24 · WS 2019 8 · Tosho Hirasawa, Mamoru Komachi

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings …

Machine TranslationMultimodal Machine TranslationNMTTranslation+1

Low-rank Optimal Transport: Approximation, Statistics and Debiasing

2022-05-24 · Meyer Scetbon, Marco Cuturi

The matching principles behind optimal transport (OT) play an increasingly important role in machine learning, a trend which can be observed when OT is used to disambiguate datasets in applications (e.g. single-cell geno…

Self-Supervised Learning

Debiasing Sentence Embedders through Contrastive Word Pairs

2024-03-27 · Philip Kenneweg, Sarah Schröder, Alexander Schulz, Barbara Hammer

Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately, multiple sources have shown that the b…

SentenceSentence EmbeddingsWord Embeddings

Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions

2026-05-24 · Chengmei Niu, Sachin Garg, Michał Dereziński, Zhenyu Liao arxiv

Random sampling is a fundamental tool in modern machine learning and numerical linear algebra for reducing the computational cost of large-scale matrix problems. Existing analyses, however, rely primarily on subspace emb…