English
Related papers

Related papers: Make Optimization Once and for All with Fine-grain…

200 papers

Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…

Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO)…

Machine Learning · Computer Science 2026-02-17 Valery Parfenov , Grigoriy Evseev , Andrey Veprikov , Nikolay Bushkov , Stanislav Moiseev , Aleksandr Beznosikov

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Robotics · Computer Science 2025-05-07 Sachit Kuhar , Shuo Cheng , Shivang Chopra , Matthew Bronars , Danfei Xu

Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$…

Machine Learning · Computer Science 2021-11-30 Zhuang Liu , Xuanlin Li , Bingyi Kang , Trevor Darrell

Large Language Models (LLMs) optimized to output truthful answers often overfit, producing brittle reasoning that fails to generalize. While persuasion-based optimization has shown promise in debate settings, it has not been systematically…

Artificial Intelligence · Computer Science 2025-10-21 Aksel Joonas Reedi , Corentin Léger , Julien Pourcel , Loris Gaven , Perrine Charriau , Guillaume Pourcel

Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is…

Computation and Language · Computer Science 2025-09-05 Wei Huang , Huang Wei , Yinggui Wang

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rewarding the choice of a single shallow classifier, we are…

Machine Learning · Computer Science 2020-04-20 Bartosz Wójcik , Maciej Wołczyk , Klaudia Bałazy , Jacek Tabor

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Xiaoling Hu , Xiangrui Zeng , Oula Puonti , Juan Eugenio Iglesias , Bruce Fischl , Yael Balbastre

In recent years, deep learning has made remarkable progress in a wide range of domains, with a particularly notable impact on natural language processing tasks. One of the challenges associated with training deep neural networks in the…

Machine Learning · Computer Science 2024-06-27 Hanna Mazzawi , Xavi Gonzalvo , Michael Wunder , Sammy Jerome , Benoit Dherin

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair…

Computation and Language · Computer Science 2026-04-13 Chia-Hsuan Lee , Mingyang Zhou , Renkun Ni , Zelei Cheng , Sihui Dai , Supriyo Chakraborty , Shixiong Zhang , Sambit Sahu , William Campbell

Neural networks offer good approximation to many tasks but consistently fail to reach perfect generalization, even when theoretical work shows that such perfect solutions can be expressed by certain architectures. Using the task of formal…

Computation and Language · Computer Science 2024-06-07 Nur Lan , Emmanuel Chemla , Roni Katzir

Hyperparameter optimization (HPO) plays a central role in the performance of deep learning models, yet remains computationally expensive and difficult to interpret, particularly for time-series forecasting. While Bayesian Optimization (BO)…

Machine Learning · Computer Science 2026-02-17 Ons Saadallah , Mátyás andó , Tamás Gábor Orosz

Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on…

Machine Learning · Computer Science 2026-05-12 Yeping Jin , Jiaming Hu , Ioannis Ch. Paschalidis

This paper studies decentralized online convex optimization in a networked multi-agent system and proposes a novel algorithm, Learning-Augmented Decentralized Online optimization (LADO), for individual agents to select actions only based on…

Machine Learning · Computer Science 2024-10-21 Pengfei Li , Jianyi Yang , Adam Wierman , Shaolei Ren

For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which…

Machine Learning · Computer Science 2025-03-24 Branton DeMoss , Paul Duckworth , Jakob Foerster , Nick Hawes , Ingmar Posner

Recent years have seen a growing interest in understanding acceleration methods through the lens of ordinary differential equations (ODEs). Despite the theoretical advancements, translating the rapid convergence observed in continuous-time…

Optimization and Control · Mathematics 2024-06-05 Zhonglin Xie , Wotao Yin , Zaiwen Wen

Optimization problems are prevalent across various scenarios. Formulating and then solving optimization problems described by natural language often requires highly specialized human expertise, which could block the widespread application…

Artificial Intelligence · Computer Science 2025-03-04 Caigao Jiang , Xiang Shu , Hong Qian , Xingyu Lu , Jun Zhou , Aimin Zhou , Yang Yu

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups).…

Machine Learning · Computer Science 2020-04-03 Shiori Sagawa , Pang Wei Koh , Tatsunori B. Hashimoto , Percy Liang

Solving massive-scale optimization problems requires scalable first-order methods with low per-iteration cost. This tutorial highlights a shift in optimization: using differentiable programming not only to execute algorithms but to learn…

Mathematical Software · Computer Science 2026-03-02 Liping Tao , Xindi Tong , Chee Wei Tan
‹ Prev 1 8 9 10 Next ›