English
Related papers

Related papers: Beyond Squared Error: Exploring Loss Design for En…

200 papers

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Xin Wang , Fisher Yu , Zi-Yi Dou , Trevor Darrell , Joseph E. Gonzalez

This paper investigates the impact of the loss function in value-based methods for reinforcement learning through an analysis of underlying prediction objectives. We theoretically show that mean absolute error is a better prediction…

Machine Learning · Computer Science 2025-11-11 Alex Ayoub , David Szepesvári , Alireza Bakhtiari , Csaba Szepesvári , Dale Schuurmans

Deep learning has achieved many breakthroughs in modern classification tasks. Numerous architectures have been proposed for different data structures but when it comes to the loss function, the cross-entropy loss is the predominant choice.…

Machine Learning · Statistics 2021-12-08 Tianyang Hu , Jun Wang , Wenjia Wang , Zhenguo Li

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 Dilin Wang , Chengyue Gong , Meng Li , Qiang Liu , Vikas Chandra

We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as…

Machine Learning · Computer Science 2018-03-06 Rémi Leblond , Jean-Baptiste Alayrac , Anton Osokin , Simon Lacoste-Julien

Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only…

Machine Learning · Statistics 2020-07-27 Ricky T. Q. Chen , Jens Behrmann , David Duvenaud , Jörn-Henrik Jacobsen

One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes and their products that control gene expression and cellular function. We can treat this as a causal…

Machine Learning · Computer Science 2023-12-27 Lazar Atanackovic , Alexander Tong , Bo Wang , Leo J. Lee , Yoshua Bengio , Jason Hartford

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Optimization and Control · Mathematics 2019-07-26 S. Günther , L. Ruthotto , J. B. Schroder , E. C. Cyr , N. R. Gauger

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models. Current state-of-the-art models primarily rely on optimizing heuristics, such as the Fr\'echet…

Machine Learning · Computer Science 2023-11-02 Alexandre Verine , Benjamin Negrevergne , Muni Sreenivas Pydi , Yann Chevaleyre

Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including…

Machine Learning · Computer Science 2022-03-29 Sam Bond-Taylor , Adam Leach , Yang Long , Chris G. Willcocks

For the purpose of effective suppression of the cycle-skipping phenomenon in full waveform inversion (FWI), we developed a Deep Neural Network (DNN) approach to predict the absent low-frequency components by exploiting the implicit relation…

Geophysics · Physics 2019-12-23 Wenyi Hu , Yuchen Jin , Xuqing Wu , Jiefu Chen

This paper provides a least squares formulation for the training of a 2-layer convolutional neural network using quadratic activation functions, a 2-norm loss function, and no regularization term. Using this method, an analytic expression…

Machine Learning · Computer Science 2024-11-18 Zachary Yetman Van Egmond , Luis Rodrigues

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize…

Machine Learning · Computer Science 2023-04-25 Shaoyi Huang , Bowen Lei , Dongkuan Xu , Hongwu Peng , Yue Sun , Mimi Xie , Caiwen Ding

We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer…

Machine Learning · Computer Science 2022-09-27 William Peebles , Ilija Radosavovic , Tim Brooks , Alexei A. Efros , Jitendra Malik

Convolutional neural networks are widely used in imaging and image recognition. Learning such networks from training data leads to the minimization of a non-convex function. This makes the analysis of standard optimization methods such as…

Optimization and Control · Mathematics 2026-01-14 Jona-Maria Diederen , Holger Rauhut , Ulrich Terstiege

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks such as weight…

Machine Learning · Computer Science 2021-05-10 Duong H. Le , Binh-Son Hua

Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this…

Machine Learning · Computer Science 2026-05-05 Jiadong Hong , Lei Liu , Xinyu Bian , Wenjie Wang , Zhaoyang Zhang

Rapid advancements in genome sequencing have led to the collection of vast amounts of genomics data. Researchers may be interested in using machine learning models on such data to predict the pathogenicity or clinical significance of a…

Quantitative Methods · Quantitative Biology 2024-08-15 Arshmeet Kaur , Morteza Sarmadi

Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as…

Machine Learning · Computer Science 2024-12-30 Dinghuai Zhang , Yizhe Zhang , Jiatao Gu , Ruixiang Zhang , Josh Susskind , Navdeep Jaitly , Shuangfei Zhai

Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large-scale diffusion and flow matching models. However, such modern generative models suffer from…

Machine Learning · Computer Science 2025-10-31 Danyal Rehman , Oscar Davis , Jiarui Lu , Jian Tang , Michael Bronstein , Yoshua Bengio , Alexander Tong , Avishek Joey Bose
‹ Prev 1 8 9 10 Next ›