Skip to yearly menu bar Skip to main content


Oral

Oral 3C

Halle A 2

Moderator: Carlo D'Eramo

Wed 8 May 1 a.m. PDT — 1:45 a.m. PDT

Abstract:

Chat is not available.

Wed 8 May 1:00 - 1:15 PDT

Improving Convergence and Generalization Using Parameter Symmetries

Bo Zhao · Robert M. Gower · Robin Walters · Rose Yu

In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model parameters. Teleportation applies such transformations to accelerate optimization. However, the exact mechanism behind this algorithm's success is not well understood. In this paper, we show that teleportation not only speeds up optimization in the short-term, but gives overall faster time to convergence. Additionally, teleporting to minima with different curvatures improves generalization, which suggests a connection between the curvature of the minimum and generalization ability. Finally, we show that integrating teleportation into a wide range of optimization algorithms and optimization-based meta-learning improves convergence. Our results showcase the versatility of teleportation and demonstrate the potential of incorporating symmetry in optimization.

Wed 8 May 1:15 - 1:30 PDT

Honorable Mention
Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Yichen Wu · Long-Kai Huang · Renzhen Wang · Deyu Meng · Ying Wei

Regularization-based methods have so far been among the de facto choices for continual learning. Recent theoretical studies have revealed that these methods all boil down to relying on the Hessian matrix approximation of model weights. However, these methods suffer from suboptimal trade-offs between knowledge transfer and forgetting due to fixed and unchanging Hessian estimations during training.Another seemingly parallel strand of Meta-Continual Learning (Meta-CL) algorithms enforces alignment between gradients of previous tasks and that of the current task. In this work we revisit Meta-CL and for the first time bridge it with regularization-based methods. Concretely, Meta-CL implicitly approximates Hessian in an online manner, which enjoys the benefits of timely adaptation but meantime suffers from high variance induced by random memory buffer sampling. We are thus highly motivated to combine the best of both worlds, through the proposal of Variance Reduced Meta-CL (VR-MCL) to achieve both timely and accurate Hessian approximation.Through comprehensive experiments across three datasets and various settings, we consistently observe that VR-MCL outperforms other SOTA methods, which further validates the effectiveness of VR-MCL.

Wed 8 May 1:30 - 1:45 PDT

Honorable Mention
Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

Ian Gemp · Luke Marris · Georgios Piliouras

We propose the first loss function for approximate Nash equilibria of normal-form games that is amenable to unbiased Monte Carlo estimation. This construction allows us to deploy standard non-convex stochastic optimization techniques for approximating Nash equilibria, resulting in novel algorithms with provable guarantees. We complement our theoretical analysis with experiments demonstrating that stochastic gradient descent can outperform previous state-of-the-art approaches.