paper-with-me

홈 › Papers

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

2021-06-04 · Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski, Jared Davis, Adrian Weller

Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length $r$ of its inner optimization loop. To address this complexity, an earlier first-order method (FOM) was proposed as a heuristic that omits second derivative terms, yielding significant speed gains and requiring only constant memory. Despite FOM's popularity, there is a lack of theoretical understanding of its convergence properties. We contribute by theoretically characterizing FOM's gradient bias under mild assumptions. We further demonstrate a rich family of examples where FOM-based SGD does not converge to a stationary point of the ABLO objective. We address this concern by proposing an unbiased FOM (UFOM) enjoying constant memory complexity as a function of $r$. We characterize the introduced time-variance tradeoff, demonstrate convergence bounds, and find an optimal UFOM for a given ABLO problem. Finally, we propose an efficient adaptive UFOM scheme.

📄 PDF Abstract BibTeX arXiv:2106.02487

Code (1)

xingyousong/ufom 공식 구현 tf

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering

2026-05-11 · Md Aminul Islam, Ahmed Sayeed Faruk, Sourav Medya, Elena Zheleva arxiv

Collaborative filtering (CF) models based on graph neural networks (GNNs) achieve strong performance in recommender systems by propagating user-item signals over interaction graphs. However, they are highly susceptible t…

Collaborative Filtering

A Heuristic Perspective on Debiasing Language Models

2026-08-01 · Tian Lan, Yemin Wang, Chuancheng Shi, Xiangyu Wu 외 arxiv

Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing methods often rely on counterfactual augmentation or representation p…

Natural Language Understanding

Spectrum-Aware Debiasing: A Modern Inference Framework with Applications to Principal Components Regression

2023-09-14 · Yufan Li, Pragya Sur

Debiasing is a fundamental concept in high-dimensional statistics. While degrees-of-freedom adjustment is the state-of-the-art technique in high-dimensional linear regression, it is limited to i.i.d. samples and sub-Gaus…

compressed sensingregression

Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness

2024-06-06 · Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue 외

While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language modeling ability and the risk of relearning social biases from downstream task-specific data…

Language ModelingLanguage Modelling

The Fundamental Limits of Structure-Agnostic Functional Estimation

2023-05-06 · Sivaraman Balakrishnan, Edward H. Kennedy, Larry Wasserman

Many recent developments in causal inference, and functional estimation problems more generally, have been motivated by the fact that classical one-step (first-order) debiasing methods, or their more recent sample-split …

Causal Inference