stp2y

arXiv:2405.19440v1 Announce Type: new Abstract: Multi-objective optimization (MOO) is receiving more attention in various fields such as multi-task learning. Recent works provide some effective algorithms with theoretical analysis but they are limited by the standard $L$-smooth or bounded-gradient assumptions, which are typically unsatisfactory for neural networks, such as recurrent neural networks (RNNs) and transformers. In this paper, we study a more general and realistic class of $ell$-smooth loss functions, where $ell$ is a general non-decreasing function of gradient norm. We develop two novel single-loop algorithms for $ell$-smooth MOO problems, Generalized Smooth Multi-objective Gradient descent (GSMGrad) and its stochastic variant, Stochastic…

arXiv:2405.19424v1 Announce Type: new Abstract: Diffusion models (DMs) have emerged as a promising approach for behavior cloning (BC). Diffusion policies (DP) based on DMs have elevated BC performance to new heights, demonstrating robust efficacy across diverse tasks, coupled with their inherent flexibility and ease of implementation. Despite the increasing adoption of DP as a foundation for policy generation, the critical issue of safety remains largely unexplored. While previous attempts have targeted deep policy networks, DP used diffusion models as the policy network, making it ineffective to be attacked using previous methods because of its chained structure and randomness injected. In…

[Submitted on 29 May 2024] View a PDF of the paper titled Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning, by Everlyn Asiko Chimoto and 5 other authors View PDF HTML (experimental) Abstract:Neural Machine Translation models are extremely data and compute-hungry. However, not all data points contribute equally to model training and generalization. Data pruning to remove the low-value data points has the benefit of drastically reducing the compute budget without significant drop in model performance. In this paper, we propose a new data pruning technique: Checkpoints Across Time (CAT), that leverages early model training dynamics to…