English
Related papers

Related papers: Re-parameterizing Your Optimizers rather than Arch…

200 papers

The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from exogenous features before solving. This setting is common to many real-world decision processes, and recently it…

Machine Learning · Computer Science 2024-09-10 James Kotary , Vincenzo Di Vito , Jacob Cristopher , Pascal Van Hentenryck , Ferdinando Fioretto

Deep learning models are defined in terms of a large number of hyperparameters, such as network architectures and optimiser settings. These hyperparameters must be determined separately from the model parameters such as network weights, and…

High Energy Physics - Phenomenology · Physics 2024-10-22 Juan Cruz-Martinez , Aaron Jansen , Gijs van Oord , Tanjona R. Rabemananjara , Carlos M. R. Rocha , Juan Rojo , Roy Stegeman

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Taojiannan Yang , Sijie Zhu , Chen Chen

Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introduces problems of its own. For example, in recurrent models…

Neural and Evolutionary Computing · Computer Science 2020-06-22 Albert Gu , Caglar Gulcehre , Tom Le Paine , Matt Hoffman , Razvan Pascanu

The choices of hyperparameters have critical effects on the performance of machine learning models. In this paper, we present a general framework that is able to construct an adaptive optimizer, which automatically adjust the appropriate…

Machine Learning · Computer Science 2022-01-31 Huayuan Sun

Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart training for each new hyperparameter choice, at considerable…

Machine Learning · Computer Science 2022-04-22 Ross M. Clarke , Elre T. Oldewage , José Miguel Hernández-Lobato

Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We…

Machine Learning · Computer Science 2018-07-04 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

Recommendation models mainly deal with categorical variables, such as user/item ID and attributes. Besides the high-cardinality issue, the interactions among such categorical variables are usually long-tailed, with the head made up of…

Machine Learning · Computer Science 2019-05-29 Yihong Chen , Bei Chen , Xiangnan He , Chen Gao , Yong Li , Jian-Guang Lou , Yue Wang

Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-learning, we propose that models should acquire not only…

Computation and Language · Computer Science 2024-12-19 Kejie Chen , Lin Wang , Qinghai Zhang , Renjun Xu

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

We propose a novel 3d shape representation for 3d shape reconstruction from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be fed into another learning algorithm to define…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Biao Zhang , Peter Wonka

Model regularization requires extensive manual tuning to balance complexity against overfitting. Cross-regularization resolves this tradeoff by directly adapting regularization parameters through validation gradients during training. The…

Machine Learning · Computer Science 2025-06-25 Carlos Stein Brito

Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradient descent requires care, as degenerate derivatives of the…

Machine Learning · Computer Science 2024-12-16 Anselm Paulus , Georg Martius , Vít Musil

Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this work, we propose a new benchmarking protocol to evaluate both…

Machine Learning · Computer Science 2020-10-21 Yuanhao Xiong , Xuanqing Liu , Li-Cheng Lan , Yang You , Si Si , Cho-Jui Hsieh

Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain level of input…

Machine Learning · Computer Science 2017-04-24 Jonathon Cai , Richard Shin , Dawn Song

Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when using optimizers relying only on local information, such as SGD. Indeed, this was a primary source of…

In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

Optimization plays a costly and crucial role in developing machine learning systems. In learned optimizers, the few hyperparameters of commonly used hand-designed optimizers, e.g. Adam or SGD, are replaced with flexible parametric…

Machine Learning · Computer Science 2022-07-19 Luke Metz , C. Daniel Freeman , James Harrison , Niru Maheswaranathan , Jascha Sohl-Dickstein