English
Related papers

Related papers: Fitting networks with a cancellation trick

200 papers

Deep representation learning using triplet network for classification suffers from a lack of theoretical foundation and difficulty in tuning both the network and classifiers for performance. To address the problem, local-margin triplet loss…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Phawis Thammasorn , Daniel Hippe , Wanpracha Chaovalitwongse , Matthew Spraker , Landon Wootton , Matthew Nyflot , Stephanie Combs , Jan Peeken , Eric Ford

As language models have grown in parameters and layers, it has become much harder to train and infer with them on single GPUs. This is severely restricting the availability of large language models such as GPT-3, BERT-Large, and many…

Computation and Language · Computer Science 2022-12-29 Jasdeep Singh Grover , Bhavesh Gawri , Ruskin Raj Manku

We study fast algorithms for statistical regression problems under the strong contamination model, where the goal is to approximately optimize a generalized linear model (GLM) given adversarially corrupted samples. Prior works in this line…

Data Structures and Algorithms · Computer Science 2021-06-23 Arun Jambulapati , Jerry Li , Tselil Schramm , Kevin Tian

With the increased demand on economy and efficiency of measurement technology, Non-Intrusive Load Monitoring (NILM) has received more and more attention as a cost-effective way to monitor electricity and provide feedback to users. Deep…

Machine Learning · Computer Science 2020-09-28 Gan Zhou , Zhi Li , Meng Fu , Yanjun Feng , Xingyao Wang , Chengwei Huang

Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Amber Yijia Zheng , Yu-Shan Tai , Raymond A. Yeh

Dropout as a regularization technique is widely used in fully connected layers while is less effective in convolutional layers. Therefore more structured forms of dropout have been proposed to regularize convolutional networks. The…

Computer Vision and Pattern Recognition · Computer Science 2023-07-31 Liqi Wang , Qiya Hu

This paper introduces a novel approach for learning to rank (LETOR) based on the notion of monotone retargeting. It involves minimizing a divergence between all monotonic increasing transformations of the training scores and a parameterized…

Machine Learning · Computer Science 2012-10-19 Sreangsu Acharyya , Oluwasanmi Koyejo , Joydeep Ghosh

The paper addresses the problem of low-rank trace norm minimization. We propose an algorithm that alternates between fixed-rank optimization and rank-one updates. The fixed-rank optimization is characterized by an efficient factorization…

Optimization and Control · Mathematics 2013-06-04 B. Mishra , G. Meyer , F. Bach , R. Sepulchre

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may…

Machine Learning · Computer Science 2026-05-15 Yuxin Guo , Yihao Yue , Yunhao Ni , Yizhou Ruan , Jie Luo , Wenjun Wu , Lei Huang

Combining the strengths of model-based iterative algorithms and data-driven deep learning solutions, deep unrolling networks (DuNets) have become a popular tool to solve inverse imaging problems. While DuNets have been successfully applied…

Machine Learning · Computer Science 2024-04-02 Qingping Zhou , Jiayu Qian , Junqi Tang , Jinglai Li

A new extremely simple ensemble-based model with the uniformly generated axis-parallel hyper-rectangles as base models (HRBM) is proposed. Two types of HRBMs are studied: closed rectangles and corners. The main idea behind HRBM is to…

Machine Learning · Computer Science 2023-03-16 Andrei V. Konstantinov , Lev V. Utkin

We introduce a rank-based bent linear regression with an unknown change point. Using a linear reparameterization technique, we propose a rank-based estimate that can make simultaneous inference on all model parameters, including the…

Methodology · Statistics 2016-06-08 Feipeng Zhang , Qunhua Li

Networks with node covariates offer two advantages to community detection methods, namely, (i) exploit covariates to improve the quality of communities, and more importantly, (ii) explain the discovered communities by identifying the…

Social and Information Networks · Computer Science 2021-04-07 Shubham Gupta , Gururaj K. , Ambedkar Dukkipati , Rui M. Castro

As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. However, in this study, we discovered that many layers of…

Computation and Language · Computer Science 2024-10-14 Xin Men , Mingyu Xu , Qingyu Zhang , Bingning Wang , Hongyu Lin , Yaojie Lu , Xianpei Han , Weipeng Chen

The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease. Though non-convex optimization is NP-hard, simple algorithms -- often variants of stochastic…

Machine Learning · Computer Science 2023-03-03 Samuel K. Ainsworth , Jonathan Hayase , Siddhartha Srinivasa

A nonparametric approach to the modeling of social networks using degree-corrected stochastic blockmodels is proposed. The model for static network consists of a stochastic blockmodel using a probit regression formulation and popularity…

Applications · Statistics 2019-08-27 Linda S. L. Tan , Maria De Iorio

The stochastic block model (SBM) is a random graph model with different group of vertices connecting differently. It is widely employed as a canonical model to study clustering and community detection, and provides a fertile ground to study…

Probability · Mathematics 2023-10-26 Emmanuel Abbe

In this article an innovative method for training regressive MLP networks is presented, which is not subject to local minima. The Error-Back-Propagation algorithm, proposed by William-Hinton-Rummelhart, has had the merit of favouring the…

Machine Learning · Computer Science 2023-08-23 Augusto Montisci

New phase transition phenomena have recently been discovered for the stochastic block model, for the special case of two non-overlapping symmetric communities. This gives raise in particular to new algorithmic challenges driven by the…

Probability · Mathematics 2015-04-07 Emmanuel Abbe , Colin Sandon

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Xiaoxu Li , Liyun Yu , Xiaochen Yang , Zhanyu Ma , Jing-Hao Xue , Jie Cao , Jun Guo