相关论文: Distilling Reinforcement Learning into Single-Batc…

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…

Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evaluating on the original testing data distribution to achieve…

Deep learning techniques have achieved great success in many fields, while at the same time deep learning models are getting more complex and expensive to compute. It severely hinders the wide applications of these models. In order to…

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…

Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also…

The popularity of deep learning has led to the curation of a vast number of massive and multifarious datasets. Despite having close-to-human performance on individual tasks, training parameter-hungry models on large datasets poses…

Modern deep recommender models are trained under a continual learning paradigm, relying on massive and continuously growing streaming behavioral logs. In large-scale platforms, retraining models on full historical data for architecture…

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new data during training. The amount of patterns stored in the…

Dataset distillation, a pragmatic approach in machine learning, aims to create a smaller synthetic dataset from a larger existing dataset. However, existing distillation methods primarily adopt a model-based paradigm, where the synthetic…

Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire…

Dataset distillation or condensation aims to condense a large-scale training dataset into a much smaller synthetic one such that the training performance of distilled and original sets on neural networks are similar. Although the number of…

Given a training dataset, the goal of dataset distillation is to derive a synthetic dataset such that models trained on the latter perform as well as those trained on the training dataset. In this work, we develop and analyze an efficient…

Dataset distillation methods have demonstrated remarkable performance for neural networks trained with very limited training data. However, a significant challenge arises in the form of \textit{architecture overfitting}: the distilled…

Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density,…

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Deep reinforcement learning is an effective tool to learn robot control policies from scratch. However, these methods are notorious for the enormous amount of required training data which is prohibitively expensive to collect on real…

Dataset distillation (DD) is a newly emerging research area aiming at alleviating the heavy computational load in training models on large datasets. It tries to distill a large dataset into a small and condensed one so that models trained…

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…