English
Related papers

Related papers: Structured First-Layer Initialization Pre-Training…

200 papers

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai

The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels accompany input data, classifying them as positive or…

Machine Learning · Computer Science 2024-05-22 Ali Karkehabadi , Houman Homayoun , Avesta Sasan

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids…

Machine Learning · Computer Science 2025-05-23 Arash Badie-Modiri , Chiara Boldrini , Lorenzo Valerio , János Kertész , Márton Karsai

Structured low-rank (SLR) algorithms, which exploit annihilation relations between the Fourier samples of a signal resulting from different properties, is a powerful image reconstruction framework in several applications. This scheme relies…

Machine Learning · Computer Science 2020-08-11 Aniket Pramanik , Hemant Aggarwal , Mathews Jacob

Training foundation models is computationally intensive and often slow to converge. We introduce PIQL,Privileged Information for Quick and Quality Learning, the first framework to systematically integrate privileged information (PI) to…

Machine Learning · Computer Science 2026-05-15 Xueying Ding , Leman Akoglu

Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based…

Machine Learning · Computer Science 2026-05-14 Yatin Dandi , Matteo Vilucchio , Luca Arnaboldi , Hugo Tabanelli , Florent Krzakala

Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end…

Neural and Evolutionary Computing · Computer Science 2024-11-12 Ruyin Wan , Qian Zhang , George Em Karniadakis

Training large language models is a computationally intensive process that often requires substantial resources to achieve state-of-the-art results. Incremental layer-wise training has been proposed as a potential strategy to optimize the…

Computation and Language · Computer Science 2024-12-02 Miles Q. Li , Benjamin C. M. Fung , Shih-Chia Huang

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…

Machine Learning · Statistics 2018-05-24 Ziv Aharoni , Gal Rattner , Haim Permuter

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

Machine Learning · Computer Science 2025-02-24 Yizhou Xu , Liu Ziyin

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit…

Databases · Computer Science 2023-09-06 Jiake Ge , Huanchen Zhang , Boyu Shi , Yuanhui Luo , Yunda Guo , Yunpeng Chai , Yuxing Chen , Anqun Pan

This paper proposes a rank inspired neural network (RINN) to tackle the initialization sensitivity issue of physics informed extreme learning machines (PIELM) when numerically solving partial differential equations (PDEs). Unlike PIELM…

Numerical Analysis · Mathematics 2025-06-24 Wentao Peng , Yunqing Huang , Nianyu Yi

Deep learning relies on good initialization schemes and hyperparameter choices prior to training a neural network. Random weight initializations induce random network ensembles, which give rise to the trainability, training speed, and…

Machine Learning · Statistics 2019-10-25 Rebekka Burkholz , Alina Dubatovka

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most…

Neural and Evolutionary Computing · Computer Science 2019-10-02 Xin Dong , Shangyu Chen , Sinno Jialin Pan

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank…

Computer Vision and Pattern Recognition · Computer Science 2020-01-27 Yuhui Xu , Yuxi Li , Shuai Zhang , Wei Wen , Botao Wang , Wenrui Dai , Yingyong Qi , Yiran Chen , Weiyao Lin , Hongkai Xiong

Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research is focussed on handcrafting complex and larger networks, and the design decisions…

Machine Learning · Computer Science 2019-04-25 Saurav Basu , Koyel Mukherjee , Shrihari Vasudevan

Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we study building blocks for self-supervised RL that unlock…

Machine Learning · Computer Science 2026-02-03 Kevin Wang , Ishaan Javali , Michał Bortkiewicz , Tomasz Trzciński , Benjamin Eysenbach

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

To improve predictive models for STEM applications, supplemental physics-based features computed from input parameters are introduced into single and multiple layers of a deep neural network (DNN). While many studies focus on informing DNNs…

Emerging Technologies · Computer Science 2024-09-02 Nicholus R. Clinkinbeard , Nicole N. Hashemi

We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs). This approach addresses the common challenges of high…

Computation and Language · Computer Science 2026-01-21 HanGyeol Yoo , ChangSu Choi , Minjun Kim , Seohyun Song , SeungWoo Song , Inho Won , Jongyoul Park , Cheoneum Park , KyungTae Lim