English
Related papers

Related papers: Efficient Per-Example Gradient Computations

200 papers

Fractional gradient descent has been studied extensively, with a focus on its ability to extend traditional gradient descent methods by incorporating fractional-order derivatives. This approach allows for more flexibility in navigating…

Machine Learning · Computer Science 2024-11-25 Teodor Alexandru Szente , James Harrison , Mihai Zanfir , Cristian Sminchisescu

For a real function, automatic differentiation is such a standard algorithm used to efficiently compute its gradient, that it is integrated in various neural network frameworks. However, despite the recent advances in using complex…

Machine Learning · Computer Science 2021-01-19 Chu Guo , Dario Poletti

Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as…

Machine Learning · Computer Science 2024-02-08 Josh Alman , Zhao Song

In this paper we focus on the linear functionals defining an approximate version of the gradient of a function. These functionals are often used when dealing with optimization problems where the computation of the gradient of the objective…

Optimization and Control · Mathematics 2021-05-21 Marco Boresta , Tommaso Colombo , Alberto De Santis , Stefano Lucidi

This paper focuses on training implicit models of infinite layers. Specifically, previous works employ implicit differentiation and solve the exact gradient for the backward propagation. However, is it necessary to compute such an exact but…

Machine Learning · Computer Science 2022-01-13 Zhengyang Geng , Xin-Yu Zhang , Shaojie Bai , Yisen Wang , Zhouchen Lin

Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. Observing the tensor contractions required to compute them, we propose a method with minimal FLOPs in 3D or greater tensor…

Machine Learning · Computer Science 2024-11-05 Gavia Gray , Aman Tiwari , Shane Bergsma , Joel Hestness

The paper proposes a numerically stable recursive algorithm for the exact computation of the linear-chain conditional random field gradient. It operates as a forward algorithm over the log-domain expectation semiring and has the purpose of…

Artificial Intelligence · Computer Science 2012-05-31 Velimir M. Ilic , Dejan I. Mancev , Branimir T. Todorovic , Miomir S. Stankovic

Gradient descent is a widely used iterative algorithm for finding local minima in multivariate functions. However, the final iterations often either overshoot the minima or make minimal progress, making it challenging to determine an…

Machine Learning · Computer Science 2024-10-28 Aviral Dhingra

Many analyses in high-energy physics rely on selection thresholds (cuts) applied to detector, particle, or event properties. Initial cut values can often be guessed from physical intuition, but cut optimization, especially for multiple…

High Energy Physics - Experiment · Physics 2025-11-12 Mike Hance , Juan Robles

Estimation of a multivariate regression function from independent and identically distributed data is considered. An estimate is defined which fits a deep neural network consisting of a large number of fully connected neural networks, which…

Statistics Theory · Mathematics 2022-08-31 Selina Drews , Michael Kohler

We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic…

Neurons and Cognition · Quantitative Biology 2007-05-23 Ila R. Fiete , H. Sebastian Seung

The likelihood ratio is a crucial quantity for statistical inference in science that enables hypothesis testing, construction of confidence intervals, reweighting of distributions, and more. Many modern scientific applications, however,…

High Energy Physics - Phenomenology · Physics 2024-12-11 Shahzar Rizvi , Mariel Pettee , Benjamin Nachman

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Machine Learning · Computer Science 2018-02-21 Yusuke Tsuzuku , Hiroto Imachi , Takuya Akiba

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…

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

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper,…

Machine Learning · Computer Science 2017-09-14 Angelos Katharopoulos , François Fleuret

This paper presents a novel coordinate descent algorithm leveraging a combination of one-directional line search and gradient information for parameter updates for a squared error loss function. Each parameter undergoes updates determined…

Machine Learning · Computer Science 2024-08-05 Yen-Che Hsiao , Abhishek Dutta

Prior work introduced a gradient descent trained expert system that conceptually combines the learning capabilities of neural networks with the understandability and defensible logic of an expert system. This system was shown to be able to…

Machine Learning · Computer Science 2022-07-08 Jeremy Straub

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Machine Learning · Computer Science 2017-09-20 Tolga Bolukbasi , Joseph Wang , Ofer Dekel , Venkatesh Saligrama

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Neural and Evolutionary Computing · Computer Science 2024-11-06 Mathew Mithra Noel , Arindam Banerjee , Yug Oswal , Geraldine Bessie Amali D , Venkataraman Muthiah-Nakarajan

Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons. To determine the global importance of each neuron or convolutional kernel, most of the existing methods either use activation or gradient…

Machine Learning · Computer Science 2023-11-01 Suman Sapkota , Binod Bhattarai