English
Related papers

Related papers: Stochastic Layer-wise Learning: Scalable and Effic…

200 papers

Robotic manipulation tasks, such as object rearrangement, play a crucial role in enabling robots to interact with complex and arbitrary environments. Existing work focuses primarily on single-level rearrangement planning and, even if…

Robotics · Computer Science 2023-09-07 Manav Kulshrestha , Ahmed H. Qureshi

Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. But one distinct advantage of unsupervised over supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Zefan Li , Chenxi Liu , Alan Yuille , Bingbing Ni , Wenjun Zhang , Wen Gao

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Machine Learning · Computer Science 2026-04-15 Qinghua Zhao , Xueling Gong , Xinyu Chen , Zhongfeng Kang , Xinlu Li

We propose an innovative, learnable two-sided short-time Laplace transform (STLT) mechanism to supplant the traditional self attention in transformer-based LLMs. Our STLT introduces trainable parameters for each Laplace node, enabling…

Machine Learning · Computer Science 2025-06-23 Andrew Kiruluta

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

Machine Learning · Computer Science 2022-02-01 Hao Liu , Huaping Liu

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

Machine Learning · Computer Science 2025-10-30 Francesco Innocenti

Deepening and widening convolutional neural networks (CNNs) significantly increases the number of trainable weight parameters by adding more convolutional layers and feature maps per layer, respectively. By imposing inter- and intra-group…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 Kevin Bui , Fredrick Park , Shuai Zhang , Yingyong Qi , Jack Xin

Recursive least squares (RLS) algorithms were once widely used for training small-scale neural networks, due to their fast convergence. However, previous RLS algorithms are unsuitable for training deep neural networks (DNNs), since they…

Machine Learning · Computer Science 2021-09-08 Chunyuan Zhang , Qi Song , Hui Zhou , Yigui Ou , Hongyao Deng , Laurence Tianruo Yang

Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing methods typically rely on low-rank,…

Computational reconstruction plays a vital role in computer vision and computational photography. Most of the conventional optimization and deep learning techniques explore local information for reconstruction. Recently, nonlocal low-rank…

Image and Video Processing · Electrical Eng. & Systems 2023-01-10 Daoyu Li , Hanwen Xu , Miao Cao , Xin Yuan , David J. Brady , Liheng Bian

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…

Machine Learning · Computer Science 2022-01-20 An Xu , Zhouyuan Huo , Heng Huang

Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for…

Machine Learning · Computer Science 2020-09-22 Alexander Ororbia , Ankur Mali , Daniel Kifer , C. Lee Giles

We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different devices. We observe that direct adaptation of self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Yun-Hao Cao , Peiqin Sun , Shuchang Zhou

Electronic computers have evolved drastically over the past years with an ever-growing demand for improved performance. However, the transfer of information from memory and high energy consumption have emerged as issues that require…

Stochastic Interpolants (SI) is a powerful framework for generative modeling, capable of flexibly transforming between two probability distributions. However, its use in jointly optimized latent variable models remains unexplored as it…

Machine Learning · Computer Science 2026-04-23 Saurabh Singh , Dmitry Lagun

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled…

Machine Learning · Computer Science 2024-12-02 Samar Hadou , Navid NaderiAlizadeh , Alejandro Ribeiro

In this paper, we introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) by dynamically expanding, activating, or skipping layers using a sophisticated routing policy…

Machine Learning · Computer Science 2024-07-17 Zhen Tan , Daize Dong , Xinyu Zhao , Jie Peng , Yu Cheng , Tianlong Chen

Second-order methods have shown state-of-the-art performance for optimizing deep neural networks. Nonetheless, their large memory requirement and high computational complexity, compared to first-order methods, hinder their versatility in a…

Machine Learning · Computer Science 2022-03-08 Ehsan Amid , Rohan Anil , Manfred K. Warmuth

Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks. However, the typical three-stage pipeline, i.e., training, pruning and retraining (fine-tuning) significantly increases the…

Machine Learning · Computer Science 2021-03-26 Deniz Gurevin , Shanglin Zhou , Lynn Pepin , Bingbing Li , Mikhail Bragin , Caiwen Ding , Fei Miao

Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Shuai Zhao , Linchao Zhu , Xiaohan Wang , Yi Yang