English
Related papers

Related papers: Continual Learning with Scaled Gradient Projection

200 papers

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Machine Learning · Computer Science 2026-05-29 Hua Li

Stochastic computation graphs (SCGs) provide a formalism to represent structured optimization problems arising in artificial intelligence, including supervised, unsupervised, and reinforcement learning. Previous work has shown that an…

Machine Learning · Computer Science 2019-01-08 Théophane Weber , Nicolas Heess , Lars Buesing , David Silver

Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several…

Machine Learning · Computer Science 2023-02-01 Xin Dong , Ruize Wu , Chao Xiong , Hai Li , Lei Cheng , Yong He , Shiyou Qian , Jian Cao , Linjian Mo

Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a…

Machine Learning · Computer Science 2020-02-19 Sebastian Flennerhag , Andrei A. Rusu , Razvan Pascanu , Francesco Visin , Hujun Yin , Raia Hadsell

In decentralized learning, a network of nodes cooperate to minimize an overall objective function that is usually the finite-sum of their local objectives, and incorporates a non-smooth regularization term for the better generalization…

Machine Learning · Computer Science 2022-01-25 Xuanjie Li , Yuedong Xu , Jessie Hui Wang , Xin Wang , John C. S. Lui

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual…

Machine Learning · Computer Science 2023-07-21 Wei Cong , Yang Cong , Gan Sun , Yuyang Liu , Jiahua Dong

High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Bowyn Tan , Yutong Xie , Bai Huang , Fan Luo , Xiao Li , Naizheng Wang , Yang Guan , Shengbo Eben Li

Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven extremely useful in many machine learning tasks over large…

Machine Learning · Computer Science 2019-06-11 Hao Peng , Jianxin Li , Hao Yan , Qiran Gong , Senzhang Wang , Lin Liu , Lihong Wang , Xiang Ren

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…

Machine Learning · Computer Science 2023-05-17 Timothée Lesort , Oleksiy Ostapenko , Diganta Misra , Md Rifat Arefin , Pau Rodríguez , Laurent Charlin , Irina Rish

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of state-space models (SSMs), a subclass of RNNs, to overcome such difficulties…

Machine Learning · Computer Science 2024-11-06 Nicolas Zucchet , Antonio Orvieto

Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task…

Machine Learning · Computer Science 2023-06-27 Tatsuya Konishi , Mori Kurokawa , Chihiro Ono , Zixuan Ke , Gyuhak Kim , Bing Liu

This paper presents a novel technique based on gradient boosting to train the final layers of a neural network (NN). Gradient boosting is an additive expansion algorithm in which a series of models are trained sequentially to approximate a…

Machine Learning · Computer Science 2023-05-05 Seyedsaman Emami , Gonzalo Martínez-Muñoz

When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks better. In such a scenario, identifying an efficient…

Machine Learning · Computer Science 2022-08-31 Pranshu Malviya , Balaraman Ravindran , Sarath Chandar

This paper presents an efficient gradient projection-based method for structural topological optimization problems characterized by a nonlinear objective function which is minimized over a feasible region defined by bilateral bounds and a…

Computational Engineering, Finance, and Science · Computer Science 2020-06-16 Zhi Zeng , Fulei Ma

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

Machine Learning · Computer Science 2024-06-26 Aashiq Muhamed , Oscar Li , David Woodruff , Mona Diab , Virginia Smith

Distributed data-parallel algorithms aim to accelerate the training of deep neural networks by parallelizing the computation of large mini-batch gradient updates across multiple nodes. Approaches that synchronize nodes using exact…

Machine Learning · Computer Science 2020-04-23 Mahmoud Assran , Nicolas Loizou , Nicolas Ballas , Michael Rabbat

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ghada Sokar , Gintare Karolina Dziugaite , Anurag Arnab , Ahmet Iscen , Pablo Samuel Castro , Cordelia Schmid

The goal of continual learning is to provide intelligent agents that are capable of learning continually a sequence of tasks using the knowledge obtained from previous tasks while performing well on prior tasks. However, a key challenge in…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Ya-nan Han , Jian-wei Liu

We devise a coreset selection method based on the idea of gradient matching: The gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of…

Machine Learning · Computer Science 2021-12-10 Lukas Balles , Giovanni Zappella , Cédric Archambeau

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an…

Computer Vision and Pattern Recognition · Computer Science 2021-06-30 Arthur Douillard , Yifu Chen , Arnaud Dapogny , Matthieu Cord