Meta-learning in neural networks: A survey
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 …
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
On implicit bias in overparameterized bilevel optimization
Many problems in machine learning involve bilevel optimization (BLO), including
hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems …
hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems …
Unbiased gradient estimation in unrolled computation graphs with persistent evolution strategies
Unrolled computation graphs arise in many scenarios, including training RNNs, tuning
hyperparameters through unrolled optimization, and training learned optimizers. Current …
hyperparameters through unrolled optimization, and training learned optimizers. Current …
Bidirectional learning for offline model-based biological sequence design
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 …
static dataset of designs and their scores. In this paper, we focus on biological sequence …
Evograd: Efficient gradient-based meta-learning and hyperparameter optimization
Gradient-based meta-learning and hyperparameter optimization have seen significant
progress recently, enabling practical end-to-end training of neural networks together with …
progress recently, enabling practical end-to-end training of neural networks together with …
Online meta-critic learning for off-policy actor-critic methods
W Zhou, Y Li, Y Yang, H Wang… - Advances in neural …, 2020 - proceedings.neurips.cc
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 …
continuous control tasks. Normally, the critic's action-value function is updated using …
Continuous-time meta-learning with forward mode differentiation
Drawing inspiration from gradient-based meta-learning methods with infinitely small
gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning …
gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning …
Low-variance gradient estimation in unrolled computation graphs with es-single
P Vicol - International Conference on Machine Learning, 2023 - proceedings.mlr.press
We propose an evolution strategies-based algorithm for estimating gradients in unrolled
computation graphs, called ES-Single. Similarly to the recently-proposed Persistent …
computation graphs, called ES-Single. Similarly to the recently-proposed Persistent …
Amortized proximal optimization
We propose a framework for online meta-optimization of parameters that govern
optimization, called Amortized Proximal Optimization (APO). We first interpret various …
optimization, called Amortized Proximal Optimization (APO). We first interpret various …
Meta-Learning for Wireless Communications: A Survey and a Comparison to GNNs
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 …
existing works assume that training and test samples are drawn from the same distribution …