English
Related papers

Related papers: Understanding Wacky Weights: A Dissection of SPLAD…

200 papers

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…

Machine Learning · Computer Science 2026-03-31 Sijia Luo , Xiaokang Zhang , Yuxuan Hu , Bohan Zhang , Ke Wang , Jinbo Su , Mengshu Sun , Lei Liang , Jing Zhang

Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investigate m-sharpness, where SAM performance improves monotonically…

Machine Learning · Computer Science 2026-04-03 Haocheng Luo , Mehrtash Harandi , Dinh Phung , Trung Le

In this thesis we discuss machine learning methods performing automated variable selection for learning sparse predictive models. There are multiple reasons for promoting sparsity in the predictive models. By relying on a limited set of…

Machine Learning · Computer Science 2019-03-27 Magda Gregorova

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

Computation and Language · Computer Science 2021-04-16 Matteo Alleman , Jonathan Mamou , Miguel A Del Rio , Hanlin Tang , Yoon Kim , SueYeon Chung

Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions. Although tremendous empirical successes have been achieved, most sparse deep…

Machine Learning · Statistics 2020-11-17 Jincheng Bai , Qifan Song , Guang Cheng

We study a set of regularization methods for high-dimensional linear regression models. These penalized estimators have the square root of the residual sum of squared errors as loss function, and any weakly decomposable norm as penalty…

Statistics Theory · Mathematics 2016-06-28 Benjamin Stucky , Sara van de Geer

Weak-to-strong (W2S) generalization is a type of finetuning (FT) where a strong (large) student model is trained on pseudo-labels generated by a weak teacher. Surprisingly, W2S FT often outperforms the weak teacher. We seek to understand…

Machine Learning · Computer Science 2026-04-21 Yijun Dong , Yicheng Li , Yunai Li , Jason D. Lee , Qi Lei

Structured sparsity has recently emerged in statistics, machine learning and signal processing as a promising paradigm for learning in high-dimensional settings. All existing methods for learning under the assumption of structured sparsity…

Machine Learning · Statistics 2015-09-16 Nino Shervashidze , Francis Bach

A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical…

Machine Learning · Computer Science 2015-08-25 Rémi Gribonval , Rodolphe Jenatton , Francis Bach

Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational…

Machine Learning · Computer Science 2025-10-03 Zachary Baker , Yuxiao Li

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

Artificial Intelligence · Computer Science 2024-04-04 Julien Ferry , Ulrich Aïvodji , Sébastien Gambs , Marie-José Huguet , Mohamed Siala

Over the past decade, learning a dictionary from input images for sparse modeling has been one of the topics which receive most research attention in image processing and compressed sensing. Most existing dictionary learning methods…

Image and Video Processing · Electrical Eng. & Systems 2021-04-27 Kai Liu , Yongjian Zhao , Hua Wang

Feature selection is a critical component in predictive analytics that significantly affects the prediction accuracy and interpretability of models. Intrinsic methods for feature selection are built directly into model learning, providing a…

Machine Learning · Computer Science 2024-03-19 Theodor Stoecker , Nico Hambauer , Patrick Zschech , Mathias Kraus

Penalized logistic regression is extremely useful for binary classification with large number of covariates (higher than the sample size), having several real life applications, including genomic disease classification. However, the…

Methodology · Statistics 2023-04-10 Ayanendranath Basu , Abhik Ghosh , María Jaenada , Leandro Pardo

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of ''$\textbf{reconstruction error…

Machine Learning · Computer Science 2025-02-21 Weizhong Huang , Yuxin Zhang , Xiawu Zheng , Fei Chao , Rongrong Ji

Understanding the reasons behind the exceptional success of transformers requires a better analysis of why attention layers are suitable for NLP tasks. In particular, such tasks require predictive models to capture contextual meaning which…

Machine Learning · Statistics 2024-05-20 Simone Bombari , Marco Mondelli

Large language models show a surprising in-context learning ability -- being able to use a prompt to form a prediction for a query, yet without additional training, in stark contrast to old-fashioned supervised learning. Providing a…

Disordered Systems and Neural Networks · Physics 2025-07-25 Yuhao Li , Ruoran Bai , Haiping Huang

The growing complexity of model parameters underscores the significance of pre-trained models. However, deployment constraints often necessitate models of varying sizes, exposing limitations in the conventional pre-training and fine-tuning…

Machine Learning · Computer Science 2025-03-18 Fu Feng , Yucheng Xie , Jing Wang , Xin Geng

We propose a new method, based on Sparse Distributed Memory (Kanerva Networks), for studying dependency relations between different syntactic parameters in the Principles and Parameters model of Syntax. We store data of syntactic parameters…

Computation and Language · Computer Science 2015-10-22 Jeong Joon Park , Ronnel Boettcher , Andrew Zhao , Alex Mun , Kevin Yuh , Vibhor Kumar , Matilde Marcolli

Stochasticity and limited precision of synaptic weights in neural network models are key aspects of both biological and hardware modeling of learning processes. Here we show that a neural network model with stochastic binary weights…

Disordered Systems and Neural Networks · Physics 2018-07-04 Carlo Baldassi , Federica Gerace , Hilbert J. Kappen , Carlo Lucibello , Luca Saglietti , Enzo Tartaglione , Riccardo Zecchina