Related papers: Budgeted Online Continual Learning by Adaptive Lay…
Vision systems mounted on home robots need to interact with unseen classes in changing environments. Robots have limited computational resources, labelled data and storage capability. These requirements pose some unique challenges: models…
We extend and combine several tools of the literature to design fast, adaptive, anytime and scale-free online learning algorithms. Scale-free regret bounds must scale linearly with the maximum loss, both toward large losses and toward very…
Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and…
Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF). Continual Learning (CL) attempts to train ASR models without suffering from CF.…
A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse…
We study the problem of full-information online learning in the "bounded recall" setting popular in the study of repeated games. An online learning algorithm $\mathcal{A}$ is $M$-$\textit{bounded-recall}$ if its output at time $t$ can be…
Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of the stored samples. Current Rehearsal-based CL methods…
Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…
Pipeline-parallel distributed optimization is essential for large-scale machine learning but is challenged by significant communication overhead from transmitting high-dimensional activations and gradients between workers. Existing…
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning…
Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…
We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily focus on regularizing model updates to preserve old…
Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural…
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot…
Practical online learning tasks are often naturally defined on unconstrained domains, where optimal algorithms for general convex losses are characterized by the notion of comparator adaptivity. In this paper, we design such algorithms in…
Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…
Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual…
Using task-specific components within a neural network in continual learning (CL) is a compelling strategy to address the stability-plasticity dilemma in fixed-capacity models without access to past data. Current methods focus only on…
Online linear programming (OLP) has found broad applications in revenue management and resource allocation. State-of-the-art OLP algorithms achieve low regret by repeatedly solving linear programming (LP) subproblems that incorporate…