paper-with-me

홈 › Papers

EXACT: How to Train Your Accuracy

2022-05-19 · Ivan Karpukhin, Stanislav Dereka, Sergey Kolesnikov

Classification tasks are usually evaluated in terms of accuracy. However, accuracy is discontinuous and cannot be directly optimized using gradient ascent. Popular methods minimize cross-entropy, hinge loss, or other surrogate losses, which can lead to suboptimal results. In this paper, we propose a new optimization framework by introducing stochasticity to a model's output and optimizing expected accuracy, i.e. accuracy of the stochastic model. Extensive experiments on linear models and deep image classification show that the proposed optimization method is a powerful alternative to widely used classification losses.

📄 PDF Abstract BibTeX arXiv:2205.09615

Code (2)

ivan-chai/exact 공식 구현 pytorch
tinkoff-ai/exact 공식 구현 pytorch

Tasks

General Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

PushupBench: Your VLM is not good at counting pushups

2026-04-25 · Shengzhi Li, Jiarun Chen, Karun Sharma, Jiaqi Su 외 arxiv

Large vision-language models (VLMs) can recognize \textit{what} happens in video but fail to count \textit{how many} times. We introduce \textbf{PushupBench}, 446 long-form clips (avg. 36.7s) for evaluating repetition co…

Slim attention: cut your context memory in half without loss of accuracy -- K-cache is all you need for MHA

2025-03-07 · Nils Graef, Andrew Wasielewski

Slim attention shrinks the context memory size by 2x for transformer models with MHA (multi-head attention), which can speed up inference by up to 2x for large context windows. Slim attention is an exact, mathematically …

AllDecoder

How to Turn Your Knowledge Graph Embeddings into Generative Models

2023-05-25 · NeurIPS 2023 11 · Lorenzo Loconte, Nicola Di Mauro, Robert Peharz, Antonio Vergari

Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact m…

Graph EmbeddingKnowledge Graph EmbeddingKnowledge Graph EmbeddingsLink Prediction

Cut your Losses with Squentropy

2023-02-08 · Like Hui, Mikhail Belkin, Stephen Wright

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests t…

ClassificationMulti-class Classification

Automated detection of dark patterns in cookie banners: how to do it poorly and why it is hard to do it any other way

2022-04-21 · Than Htut Soe, Cristiana Teixeira Santos, Marija Slavkovik

Cookie banners, the pop ups that appear to collect your consent for data collection, are a tempting ground for dark patterns. Dark patterns are design elements that are used to influence the user's choice towards an opti…

BIG-bench Machine LearningFeature Engineering