Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then
introduced into the optimization community. BLO is able to handle problems with a …
introduced into the optimization community. BLO is able to handle problems with a …
Transformers as decision makers: Provable in-context reinforcement learning via supervised pretraining
Large transformer models pretrained on offline reinforcement learning datasets have
demonstrated remarkable in-context reinforcement learning (ICRL) capabilities, where they …
demonstrated remarkable in-context reinforcement learning (ICRL) capabilities, where they …
How important is the train-validation split in meta-learning?
Meta-learning aims to perform fast adaptation on a new task through learning a “prior” from
multiple existing tasks. A common practice in meta-learning is to perform a train-validation …
multiple existing tasks. A common practice in meta-learning is to perform a train-validation …
Global convergence of maml and theory-inspired neural architecture search for few-shot learning
Abstract Model-agnostic meta-learning (MAML) and its variants have become popular
approaches for few-shot learning. However, due to the non-convexity of deep neural nets …
approaches for few-shot learning. However, due to the non-convexity of deep neural nets …
Maml and anil provably learn representations
Recent empirical evidence has driven conventional wisdom to believe that gradient-based
meta-learning (GBML) methods perform well at few-shot learning because they learn an …
meta-learning (GBML) methods perform well at few-shot learning because they learn an …
Multi-learner based deep meta-learning for few-shot medical image classification
Few-shot learning (FSL) is promising in the field of medical image analysis due to high cost
of establishing high-quality medical datasets. Many FSL approaches have been proposed in …
of establishing high-quality medical datasets. Many FSL approaches have been proposed in …
Robust reinforcement learning using least squares policy iteration with provable performance guarantees
KP Badrinath, D Kalathil - International Conference on …, 2021 - proceedings.mlr.press
This paper addresses the problem of model-free reinforcement learning for Robust Markov
Decision Process (RMDP) with large state spaces. The goal of the RMDPs framework is to …
Decision Process (RMDP) with large state spaces. The goal of the RMDPs framework is to …
Generalization of model-agnostic meta-learning algorithms: Recurring and unseen tasks
A Fallah, A Mokhtari… - Advances in Neural …, 2021 - proceedings.neurips.cc
In this paper, we study the generalization properties of Model-Agnostic Meta-Learning
(MAML) algorithms for supervised learning problems. We focus on the setting in which we …
(MAML) algorithms for supervised learning problems. We focus on the setting in which we …
Inexact-ADMM based federated meta-learning for fast and continual edge learning
In order to meet the requirements for performance, safety, and latency in many IoT
applications, intelligent decisions must be made right here right now at the network edge …
applications, intelligent decisions must be made right here right now at the network edge …
Is Bayesian model-agnostic meta learning better than model-agnostic meta learning, provably?
Meta learning aims at learning a model that can quickly adapt to unseen tasks. Widely used
meta learning methods include model agnostic meta learning (MAML), implicit MAML …
meta learning methods include model agnostic meta learning (MAML), implicit MAML …