English
Related papers

Related papers: Extending CDCL-based Model Enumeration with Weight…

200 papers

A major limitation of machine learning (ML) prediction models is that they recover associational, rather than causal, predictive relationships between variables. In high-stakes automation applications of ML this is problematic, as the model…

Machine Learning · Computer Science 2025-11-04 Jianqiao Mao , Max A. Little

Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the…

We study the high-dimensional linear regression problem with categorical predictors that have many levels. We propose a new estimation approach, which performs model compression via two mechanisms by simultaneously encouraging (a)…

Methodology · Statistics 2026-03-30 Kayhan Behdin , Riade Benbaki , Peter Radchenko , Rahul Mazumder

Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning…

Machine Learning · Statistics 2020-03-24 Diana Cai , Rishit Sheth , Lester Mackey , Nicolo Fusi

The integration of Large Language Models (LLMs) into autonomous driving systems offers promising enhancements in environmental understanding and decision-making. However, the substantial computational demands of deploying LLMs locally on…

Machine Learning · Computer Science 2025-08-06 Jiaxi Li , Lu Yin , Xilu Wang

We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine…

Machine Learning · Computer Science 2025-01-24 Hubert Baniecki , Giuseppe Casalicchio , Bernd Bischl , Przemyslaw Biecek

Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications…

Machine Learning · Computer Science 2018-11-21 Ehsan Variani , Ananda Theertha Suresh , Mitchel Weintraub

Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that merging the parameters of independently fine-tuned models can…

Machine Learning · Computer Science 2024-10-30 Li Shen , Anke Tang , Enneng Yang , Guibing Guo , Yong Luo , Lefei Zhang , Xiaochun Cao , Bo Du , Dacheng Tao

We study ranked enumeration for Conjunctive Queries (CQs) where the answers are ordered by a given ranking function (e.g., an ORDER BY clause in SQL). We develop "any-k" algorithms, which, without knowing the number k of desired answers,…

Databases · Computer Science 2023-10-16 Nikolaos Tziavelis , Wolfgang Gatterbauer , Mirek Riedewald

Since the Fourth Industrial Revolution, AI technology has been widely used in many fields, but there are several limitations that need to be overcome, including overfitting/underfitting, class imbalance, and the limitations of…

Machine Learning · Computer Science 2025-08-18 DongSeong-Yoon

A constrained multivariate linear model is a multivariate linear model with the columns of its coefficient matrix constrained to lie in a known subspace. This class of models includes those typically used to study growth curves and…

Methodology · Statistics 2021-01-05 Dennis Cook , Liliana Forzani , Lan Liu

In this paper, we propose a Dual Focal Loss (DFL) function, as a replacement for the standard cross entropy (CE) function to achieve a better treatment of the unbalanced classes in a dataset. Our DFL method is an improvement on the recently…

Computer Vision and Pattern Recognition · Computer Science 2020-11-30 Md Sazzad Hossain , Andrew P Paplinski , John M Betts

The prohibitive cost of evaluating Large Language Models (LLMs) necessitates efficient alternatives to full-scale benchmarking. Prevalent approaches address this by identifying a small coreset of items to approximate full-benchmark…

Artificial Intelligence · Computer Science 2026-02-04 Yueqi Zhang , Jin Hu , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Yiwei Li , Jiayi Shi , Chuyi Tan , Ji Zhang , Boyuan Pan , Yao Hu , Kan Li

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Machine Learning · Computer Science 2025-04-04 Jiho Choi , Donggyun Kim , Chanhyuk Lee , Seunghoon Hong

We characterize how memorization is represented in transformer models and show that it can be disentangled in the weights of both language models (LMs) and vision transformers (ViTs) using a decomposition based on the loss landscape…

Computation and Language · Computer Science 2025-11-03 Jack Merullo , Srihita Vatsavaya , Lucius Bushnaq , Owen Lewis

We primarily study a special a weighted low-rank approximation of matrices and then apply it to solve the background modeling problem. We propose two algorithms for this purpose: one operates in the batch mode on the entire data and the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-18 Aritra Dutta , Xin Li , Peter Richtarik

Mobile-edge computing (MEC) offloads computational tasks from wireless devices to network edge, and enables real-time information transmission and computing. Most existing work concerns a small-scale synchronous MEC system. In this paper,…

Information Theory · Computer Science 2021-02-03 Yizhen Xu , Peng Cheng , Zhuo Chen , Ming Ding , Branka Vucetic , Yonghui Li

Large language models (LLMs) contain billions of parameters, yet many exact values are not essential. We show that what matters most is the relative rank of weights-whether one connection is stronger or weaker than another-rather than…

Machine Learning · Computer Science 2026-03-19 Borja Aizpurua , Sukhbinder Singh , Román Orús

Mixture-of-Experts (MoE) architectures in large language models (LLMs) achieve exceptional performance, but face prohibitive storage and memory requirements. To address these challenges, we present $D^2$-MoE, a new delta decompression…

Machine Learning · Computer Science 2025-02-25 Hao Gu , Wei Li , Lujun Li , Qiyuan Zhu , Mark Lee , Shengjie Sun , Wei Xue , Yike Guo

Mixed effects (ME) models inform a vast array of problems in the physical and social sciences, and are pervasive in meta-analysis. We consider ME models where the random effects component is linear. We then develop an efficient approach for…