English
Related papers

Related papers: Noise Stability Optimization for Finding Flat Mini…

200 papers

Despite a variety of available techniques the issue of the proper regularization parameter choice for inverse problems still remains one of the biggest challenges. The main difficulty lies in constructing a rule, allowing to compute the…

Numerical Analysis · Mathematics 2017-10-13 Ernesto De Vito , Massimo Fornasier , Valeriya Naumova

Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 William Peebles , John Peebles , Jun-Yan Zhu , Alexei Efros , Antonio Torralba

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

Machine Learning · Statistics 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

The Hessian-vector product has been utilized to find a second-order stationary solution with strong complexity guarantee (e.g., almost linear time complexity in the problem's dimensionality). In this paper, we propose to further reduce the…

Optimization and Control · Mathematics 2017-10-03 Mingrui Liu , Tianbao Yang

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In…

Machine Learning · Computer Science 2022-12-29 Harsh Rangwani , Sumukh K Aithal , Mayank Mishra , R. Venkatesh Babu

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

In this work, we investigate the mechanism underlying loss spikes observed during neural network training. When the training enters a region with a lower-loss-as-sharper (LLAS) structure, the training becomes unstable, and the loss…

Machine Learning · Computer Science 2024-10-08 Xiaolong Li , Zhi-Qin John Xu , Zhongwang Zhang

We analyze Newton's method with lazy Hessian updates for solving general possibly non-convex optimization problems. We propose to reuse a previously seen Hessian for several iterations while computing new gradients at each step of the…

Optimization and Control · Mathematics 2023-06-16 Nikita Doikov , El Mahdi Chayti , Martin Jaggi

Consider estimating a structured signal $\mathbf{x}_0$ from linear, underdetermined and noisy measurements $\mathbf{y}=\mathbf{A}\mathbf{x}_0+\mathbf{z}$, via solving a variant of the lasso algorithm: $\hat{\mathbf{x}}=\arg\min_\mathbf{x}\{…

Optimization and Control · Mathematics 2014-01-28 Christos Thrampoulidis , Samet Oymak , Babak Hassibi

Classical model-based imaging methods for ultrasound elasticity inverse problem require prior constraints about the underlying elasticity patterns, while finding the appropriate hand-crafted prior for each tissue type is a challenge. In…

Image and Video Processing · Electrical Eng. & Systems 2021-06-16 Narges Mohammadi , Marvin M. Doyley , Mujdat Cetin

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

Analysis of non-asymptotic estimation error and structured statistical recovery based on norm regularized regression, such as Lasso, needs to consider four aspects: the norm, the loss function, the design matrix, and the noise model. This…

Machine Learning · Statistics 2015-12-01 Arindam Banerjee , Sheng Chen , Farideh Fazayeli , Vidyashankar Sivakumar

In this work, we investigate data fitting problems with random noises. A randomized progressive iterative regularization method is proposed. It works well for large-scale matrix computations and converges in expectation to the least-squares…

Numerical Analysis · Mathematics 2025-06-05 Dakang Cen , Wenlong Zhang , Junbin Zhong

Sparse learning is ubiquitous in many machine learning tasks. It aims to regularize the goodness-of-fit objective by adding a penalty term to encode structural constraints on the model parameters. In this paper, we develop a flexible sparse…

Machine Learning · Statistics 2026-02-10 Yingjie Wang , Mokhtar Z. Alaya , Salim Bouzebda , Xinsheng Liu

Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-based training scheme for better model robustness.…

Machine Learning · Computer Science 2023-05-30 Zeliang Zhang , Jinyang Jiang , Minjie Chen , Zhiyuan Wang , Yijie Peng , Zhaofei Yu

Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability density from data. Though highly expressive, neural network…

Machine Learning · Statistics 2020-02-17 Jonas Rothfuss , Fabio Ferreira , Simon Boehm , Simon Walther , Maxim Ulrich , Tamim Asfour , Andreas Krause

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein

This paper presents a patch-wise low-rank based image denoising method with constrained variational model involving local and nonlocal regularization. On one hand, recent patch-wise methods can be represented as a low-rank matrix…

Computer Vision and Pattern Recognition · Computer Science 2015-12-04 Yuan Xie

In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally…

Systems and Control · Electrical Eng. & Systems 2019-09-04 Adrian Wills , Thomas Schön