English
Related papers

Related papers: Unveiling m-Sharpness Through the Structure of Sto…

200 papers

Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always yields an entirely new model for each task. Currently, many…

Computation and Language · Computer Science 2022-11-29 Zihao Fu , Haoran Yang , Anthony Man-Cho So , Wai Lam , Lidong Bing , Nigel Collier

The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivated by this observation, there has been significant recent…

Machine Learning · Computer Science 2020-12-04 Leighton Pate Barnes , Huseyin A. Inan , Berivan Isik , Ayfer Ozgur

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

Spiking neural networks (SNNs) are a natural computational model for on-sensor and near-sensor vision, where event driven processors must operate under strict power budgets with hard binary spikes. However, models trained with surrogate…

Neural and Evolutionary Computing · Computer Science 2026-04-14 Maximilian Nicholson

Models incorporating uncertain inputs, such as random forces or material parameters, have been of increasing interest in PDE-constrained optimization. In this paper, we focus on the efficient numerical minimization of a convex and smooth…

Optimization and Control · Mathematics 2021-06-18 Caroline Geiersbach , Winnifried Wollner

We consider network sparsification as an $L_0$-norm regularized binary optimization problem, where each unit of a neural network (e.g., weight, neuron, or channel, etc.) is attached with a stochastic binary gate, whose parameters are…

Machine Learning · Computer Science 2021-07-02 Yang Li , Shihao Ji

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 David Qiu , David Rim , Shaojin Ding , Oleg Rybakov , Yanzhang He

We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential equations driven by…

Machine Learning · Statistics 2021-12-02 Soon Hoe Lim , N. Benjamin Erichson , Liam Hodgkinson , Michael W. Mahoney

Randomized smoothing (RS) has successfully been used to improve the robustness of predictions for deep neural networks (DNNs) by adding random noise to create multiple variations of an input, followed by deciding the consensus. To…

Machine Learning · Computer Science 2024-04-29 Emmanouil Seferis , Stefanos Kollias , Chih-Hong Cheng

Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achieving adversarial…

Neural and Evolutionary Computing · Computer Science 2025-12-04 Luu Trong Nhan , Luu Trung Duong , Pham Ngoc Nam , Truong Cong Thang

State-space models (SSMs) are a common tool for modeling multi-variate discrete-time signals. The linear-Gaussian (LG) SSM is widely applied as it allows for a closed-form solution at inference, if the model parameters are known. However,…

Computational Engineering, Finance, and Science · Computer Science 2023-03-23 Emilie Chouzenoux , Victor Elvira

This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. To…

Machine Learning · Computer Science 2024-07-19 Wanyun Xie , Fabian Latorre , Kimon Antonakopoulos , Thomas Pethick , Volkan Cevher

Neural networks are widespread due to their powerful performance. Yet, they degrade in the presence of noisy labels at training time. Inspired by the setting of learning with expert advice, where multiplicative weights (MW) updates were…

Machine Learning · Computer Science 2025-11-12 Noga Bar , Tomer Koren , Raja Giryes

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Ron Keuth , Lasse Hansen , Maren Balks , Ronja Jäger , Anne-Nele Schröder , Ludger Tüshaus , Mattias Heinrich

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Machine Learning · Computer Science 2020-10-01 Lang Huang , Chao Zhang , Hongyang Zhang

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability.…

Machine Learning · Computer Science 2020-09-08 Wonyong Sung , Iksoo Choi , Jinhwan Park , Seokhyun Choi , Sungho Shin

We consider the problem of reconstructing a discrete-time signal (sequence) with continuous-valued components corrupted by a known memoryless channel. When performance is measured using a per-symbol loss function satisfying mild regularity…

Information Theory · Computer Science 2008-07-23 Kamakshi Sivaramakrishnan , Tsachy Weissman

Automatic speech recognition systems based on deep learning are mainly trained under empirical risk minimization (ERM). Since ERM utilizes the averaged performance on the data samples regardless of a group such as healthy or dysarthric…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-28 Eungbeom Kim , Yunkee Chae , Jaeheon Sim , Kyogu Lee

To improve the off-sample generalization of classical procedures minimizing the empirical risk under potentially heavy-tailed data, new robust learning algorithms have been proposed in recent years, with generalized median-of-means…

Machine Learning · Statistics 2018-10-16 Matthew J. Holland

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

‹ Prev 1 8 9 10 Next ›