English
Related papers

Related papers: Polynomial Surrogate Training for Differentiable T…

200 papers

The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE)…

Machine Learning · Computer Science 2026-05-26 Haoyu Huang , Boyu Liu , Linlin Yang , Yanjing Li , Yuguang Yang , Xuhui Liu , Canyu Chen , Zhongqian Fu , Baochang Zhang

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both…

Machine Learning · Computer Science 2018-09-11 Jorn W. T. Peters , Max Welling

Structured prediction involves learning to predict complex structures rather than simple scalar values. The main challenge arises from the non-Euclidean nature of the output space, which generally requires relaxing the problem formulation.…

Machine Learning · Statistics 2024-11-19 Junjie Yang , Matthieu Labeau , Florence d'Alché-Buc

Neural networks increasingly embed non-differentiable components (spiking neurons, quantized layers, discrete routing, blackbox simulators, etc.) where backpropagation is inapplicable and surrogate gradients introduce bias. We present…

Machine Learning · Computer Science 2026-05-05 An T. Le

We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has $k$ hidden layers and that the $\ell_1$-norm of the incoming weights of any neuron is bounded by $L$. We present a kernel-based…

Machine Learning · Computer Science 2015-10-14 Yuchen Zhang , Jason D. Lee , Michael I. Jordan

Brain-inspired Spiking Neural Networks (SNNs) have attracted much attention due to their event-based computing and energy-efficient features. However, the spiking all-or-none nature has prevented direct training of SNNs for various…

Neural and Evolutionary Computing · Computer Science 2024-07-01 Yang Li , Feifei Zhao , Dongcheng Zhao , Yi Zeng

This paper presents a theoretical analysis and practical evaluation of the main bottlenecks towards a scalable distributed solution for the training of Deep Neuronal Networks (DNNs). The presented results show, that the current state of the…

Computer Vision and Pattern Recognition · Computer Science 2016-12-06 Janis Keuper , Franz-Josef Pfreundt

Evolutionary algorithms are increasingly recognised as a viable computational approach for the automated optimisation of deep neural networks (DNNs) within artificial intelligence. This method extends to the training of DNNs, an approach…

Neural and Evolutionary Computing · Computer Science 2024-03-29 Fergal Stapleton , Brendan Cody-Kenny , Edgar Galván

Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network from a pre-trained…

Machine Learning · Computer Science 2021-06-16 Shiwei Liu , Decebal Constantin Mocanu , Yulong Pei , Mykola Pechenizkiy

The learning rate (LR) is one of the most important hyper-parameters in stochastic gradient descent (SGD) algorithm for training deep neural networks (DNN). However, current hand-designed LR schedules need to manually pre-specify a fixed…

Machine Learning · Computer Science 2021-05-14 Jun Shu , Yanwen Zhu , Qian Zhao , Zongben Xu , Deyu Meng

We study learnable logic gate networks that stack layers of 2-input Boolean gates to build combinational circuits. Every 2-input gate has a unique multilinear polynomial with 4 coefficients, so the 16 Boolean gates form a codebook of…

Machine Learning · Computer Science 2026-05-12 Youngsung Kim

Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications. The effectiveness of DNN methods can be…

Machine Learning · Statistics 2017-06-01 Henghui Zhu , Feng Nan , Ioannis Paschalidis , Venkatesh Saligrama

Recent work by Lakshminarayanan and Singh [2020] provided a dual view for fully connected deep neural networks (DNNs) with rectified linear units (ReLU). It was shown that (i) the information in the gates is analytically characterised by a…

Machine Learning · Computer Science 2022-03-31 Chandrashekar Lakshminarayanan , Amit Vikram Singh , Arun Rajkumar

This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds via gradient descent, unlike conventional methods where they…

Machine Learning · Computer Science 2021-03-22 Kambiz Azarian , Yash Bhalgat , Jinwon Lee , Tijmen Blankevoort

Verifying real-world programs often requires inferring loop invariants with nonlinear constraints. This is especially true in programs that perform many numerical operations, such as control systems for avionics or industrial plants.…

Software Engineering · Computer Science 2020-11-03 Jianan Yao , Gabriel Ryan , Justin Wong , Suman Jana , Ronghui Gu

Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inherit from imperfect reward estimates remains unquantified. We propagate this uncertainty…

A large fraction of the arithmetic operations required to evaluate deep neural networks (DNNs) consists of matrix multiplications, in both convolution and fully connected layers. We perform end-to-end learning of low-cost approximations of…

Machine Learning · Computer Science 2018-06-11 Michael Tschannen , Aran Khanna , Anima Anandkumar

Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activation functions are systematically tested with…

High Energy Physics - Phenomenology · Physics 2025-10-28 Henning Bahl , Nina Elmer , Luigi Favaro , Manuel Haußmann , Tilman Plehn , Ramon Winterhalder

We study the problem of learning a low-degree spherical polynomial of degree $k_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network with augmented feature in this paper. Our…

Machine Learning · Statistics 2026-03-24 Yingzhen Yang , Ping Li

Spiking neural networks (SNNs) are a bio-inspired alternative to conventional real-valued deep learning models, with the potential for substantially higher energy efficiency. Interest in SNNs has recently exploded due to a major…

Neural and Evolutionary Computing · Computer Science 2025-10-16 Alexandre Queant , Ulysse Rançon , Benoit R Cottereau , Timothée Masquelier