The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Many problems in machine learning involve bilevel optimization (BLO), including
hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems …

Unrolled computation graphs arise in many scenarios, including training RNNs, tuning
hyperparameters through unrolled optimization, and training learned optimizers. Current …

Offline model-based optimization aims to maximize a black-box objective function with a
static dataset of designs and their scores. In this paper, we focus on biological sequence …

Gradient-based meta-learning and hyperparameter optimization have seen significant
progress recently, enabling practical end-to-end training of neural networks together with …

Abstract Off-Policy Actor-Critic (OffP-AC) methods have proven successful in a variety of
continuous control tasks. Normally, the critic's action-value function is updated using …

Drawing inspiration from gradient-based meta-learning methods with infinitely small
gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning …

We propose an evolution strategies-based algorithm for estimating gradients in unrolled
computation graphs, called ES-Single. Similarly to the recently-proposed Persistent …

We propose a framework for online meta-optimization of parameters that govern
optimization, called Amortized Proximal Optimization (APO). We first interpret various …

Deep learning has been used for optimizing a multitude of wireless problems. Yet most
existing works assume that training and test samples are drawn from the same distribution …