English
Related papers

Related papers: Learning Large-Scale Modular Addition with an Auxi…

200 papers

In this work, we propose an adaptive sparse learning algorithm that can be applied to learn the physical processes and obtain a sparse representation of the solution given a large snapshot space. Assume that there is a rich class of…

Machine Learning · Computer Science 2022-07-26 Yating Wang , Wing Tat Leung , Guang Lin

Sparse linear regression -- finding an unknown vector from linear measurements -- is now known to be possible with fewer samples than variables, via methods like the LASSO. We consider the multiple sparse linear regression problem, where…

Machine Learning · Computer Science 2012-02-28 Ali Jalali , Pradeep Ravikumar , Sujay Sanghavi

Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning. Although computationally efficient, the recent Adapters…

Computation and Language · Computer Science 2022-11-11 Shwai He , Liang Ding , Daize Dong , Miao Zhang , Dacheng Tao

Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters…

Machine Learning · Computer Science 2026-05-22 Kun-Peng Ning , Hai-Jian Ke , Yu-Yang Liu , Jia-Yu Yao , Yong-Hong Tian , Li Yuan

Parameter-efficient fine-tuning stands as the standard for efficiently fine-tuning large language and vision models on downstream tasks. Specifically, the efficiency of low-rank adaptation has facilitated the creation and sharing of…

Machine Learning · Computer Science 2024-02-26 Nader Asadi , Mahdi Beitollahi , Yasser Khalil , Yinchuan Li , Guojun Zhang , Xi Chen

The goal of this paper is to investigate the complexity of gradient algorithms when learning sparse functions (juntas). We introduce a type of Statistical Queries ($\mathsf{SQ}$), which we call Differentiable Learning Queries…

Machine Learning · Computer Science 2024-07-09 Nirmit Joshi , Theodor Misiakiewicz , Nathan Srebro

Remarkable gains in deep learning usually rely on tremendous supervised data. Ensuring the modality diversity for one object in training set is critical for the generalization of cutting-edge deep models, but it burdens human with heavy…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Jiang Lu , Lei Li , Changshui Zhang

Low-precision training is critical for optimizing the trade-off between model quality and training costs, necessitating the joint allocation of model size, dataset size, and numerical precision. While empirical scaling laws suggest that…

Machine Learning · Statistics 2026-02-27 Dechen Zhang , Xuan Tang , Yingyu Liang , Difan Zou

In many operational applications, it is necessary to routinely find, within a very limited time window, provably good solutions to challenging mixed-integer linear programming (MILP) problems. An example is the Security-Constrained Unit…

Optimization and Control · Mathematics 2022-08-23 Xiaoyi Gu , Santanu S. Dey , Álinson S. Xavier , Feng Qiu

We introduce an alternative to the notion of `fast rate' in Learning Theory, which coincides with the optimal error rate when the given class happens to be convex and regular in some sense. While it is well known that such a rate cannot…

Statistics Theory · Mathematics 2015-02-26 Shahar Mendelson

Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory…

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each…

Computer Vision and Pattern Recognition · Computer Science 2018-09-07 Xiangyun Zhao , Haoxiang Li , Xiaohui Shen , Xiaodan Liang , Ying Wu

Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address…

Machine Learning · Statistics 2025-04-29 Steve Hanneke , Samory Kpotufe

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Machine Learning · Computer Science 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Multitask Learning is a Machine Learning paradigm that aims to train a range of (usually related) tasks with the help of a shared model. While the goal is often to improve the joint performance of all training tasks, another approach is to…

Machine Learning · Computer Science 2024-05-14 Rafael Kourdis , Gabriel Gordon-Hall , Philip John Gorinski

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

Efficient inference is critical for long-context language models, where attention computation and KV-cache access dominate the cost. Recent work RAT+, introduces a recurrence-augmented attention backbone that enables flexible dilated…

Machine Learning · Computer Science 2026-05-28 Xiuying Wei , Caglar Gulcehre

We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel mutation operator. We incorporate the sparsity constraints into the score function, which steers the…

Machine Learning · Computer Science 2026-02-10 Huan Zhang , Yanjian Zhang , Guillaume Wisniewski , Nadi Tomeh , Bang Liu

SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input vector onto a probability simplex and reweights the input by concentrating the probability mass at large entries. Yet, as a smooth approximation to…

Machine Learning · Computer Science 2025-01-09 Yuxuan Zhou , Mario Fritz , Margret Keuper