English
Related papers

Related papers: Importance Estimation with Random Gradient for Neu…

200 papers

Modern deep neural networks are often too large to use in many practical scenarios. Neural network pruning is an important technique for reducing the size of such models and accelerating inference. Gibbs pruning is a novel framework for…

Machine Learning · Computer Science 2021-12-30 Alex Labach , Shahrokh Valaee

This paper proposes a fractional order gradient method for the backward propagation of convolutional neural networks. To overcome the problem that fractional order gradient method cannot converge to real extreme point, a simplified…

Optimization and Control · Mathematics 2020-01-07 Dian Sheng , Yiheng Wei , Yuquan Chen , Yong Wang

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Youngmin Ro , Jin Young Choi

Importance weighting is a fundamental procedure in statistics and machine learning that weights the objective function or probability distribution based on the importance of the instance in some sense. The simplicity and usefulness of the…

Machine Learning · Computer Science 2024-05-15 Masanari Kimura , Hideitsu Hino

Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is…

Machine Learning · Computer Science 2019-06-17 Jonathon Byrd , Zachary C. Lipton

In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to selectively discard redundant tokens, they largely rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Mingzhe Huang , Weijun Wang , Xin Ding , Liang Mi , Hao Wen , Yuanchun Li , Lichen Pang , Shansong Yang , Yunxin Liu , Ting Cao

We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolution that represents the differentials of rendering…

Graphics · Computer Science 2025-08-07 Zican Wang , Michael Fischer , Tobias Ritschel

Traditional neural networks are simple to train but they typically produce overconfident predictions. In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large…

Machine Learning · Computer Science 2024-11-07 Yadi Wei , Roni Khardon

With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However,…

Information Retrieval · Computer Science 2024-07-08 Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

Neural networks -- especially those that use large, pre-trained language models -- have improved search engines in various ways. Most prominently, they can estimate the relevance of a passage or document to a user's query. In this work, we…

Information Retrieval · Computer Science 2024-07-18 Xuejun Chang , Debabrata Mishra , Craig Macdonald , Sean MacAvaney

Neural Networks are known to be sensitive to initialisation. The methods that rely on neural networks for feature ranking are not robust since they can have variations in their ranking when the model is initialized and trained with…

Machine Learning · Computer Science 2022-10-14 Talip Ucar , Ehsan Hajiramezanali

Network compression is crucial to making the deep networks to be more efficient, faster, and generalizable to low-end hardware. Current network compression methods have two open problems: first, there lacks a theoretical framework to…

Machine Learning · Computer Science 2022-06-09 Ziqi Zhou , Li Lian , Yilong Yin , Ze Wang

We introduce data structures for solving robust regression through stochastic gradient descent (SGD) by sampling gradients with probability proportional to their norm, i.e., importance sampling. Although SGD is widely used for large scale…

Machine Learning · Computer Science 2022-07-19 Sepideh Mahabadi , David P. Woodruff , Samson Zhou

This paper presents a novel approach to neural network pruning by integrating a graph-based observation space into an AutoML framework to address the limitations of existing methods. Traditional pruning approaches often depend on…

Machine Learning · Computer Science 2025-09-16 Dieter Balemans , Thomas Huybrechts , Jan Steckel , Siegfried Mercelis

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative…

Computer Vision and Pattern Recognition · Computer Science 2022-02-14 Yang He , Ping Liu , Linchao Zhu , Yi Yang

Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information…

Machine Learning · Computer Science 2025-07-22 Yiding Song

We propose to use deep neural networks for generating samples in Monte Carlo integration. Our work is based on non-linear independent components estimation (NICE), which we extend in numerous ways to improve performance and enable its…

Machine Learning · Computer Science 2019-09-04 Thomas Müller , Brian McWilliams , Fabrice Rousselle , Markus Gross , Jan Novák

A novel method to identify salient computational paths within randomly wired neural networks before training is proposed. The computational graph is pruned based on a node mass probability function defined by local graph measures and…

Machine Learning · Computer Science 2020-07-09 Samuel Glass , Simeon Spasov , Pietro Liò

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

Machine Learning · Computer Science 2020-05-13 Rohun Tripathi , Bharat Singh

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…