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 …
Fednest: Federated bilevel, minimax, and compositional optimization
DA Tarzanagh, M Li… - … on Machine Learning, 2022 - proceedings.mlr.press
Standard federated optimization methods successfully apply to stochastic problems with
single-level structure. However, many contemporary ML problems-including adversarial …
single-level structure. However, many contemporary ML problems-including adversarial …
A survey of deep RL and IL for autonomous driving policy learning
Z Zhu, H Zhao - IEEE Transactions on Intelligent Transportation …, 2021 - ieeexplore.ieee.org
Autonomous driving (AD) agents generate driving policies based on online perception
results, which are obtained at multiple levels of abstraction, eg, behavior planning, motion …
results, which are obtained at multiple levels of abstraction, eg, behavior planning, motion …
Decentralized gossip-based stochastic bilevel optimization over communication networks
Bilevel optimization have gained growing interests, with numerous applications found in
meta learning, minimax games, reinforcement learning, and nested composition …
meta learning, minimax games, reinforcement learning, and nested composition …
Toward the fundamental limits of imitation learning
Imitation learning (IL) aims to mimic the behavior of an expert policy in a sequential decision-
making problem given only demonstrations. In this paper, we focus on understanding the …
making problem given only demonstrations. In this paper, we focus on understanding the …
Inverse dynamics pretraining learns good representations for multitask imitation
D Brandfonbrener, O Nachum… - Advances in Neural …, 2024 - proceedings.neurips.cc
In recent years, domains such as natural language processing and image recognition have
popularized the paradigm of using large datasets to pretrain representations that can be …
popularized the paradigm of using large datasets to pretrain representations that can be …
Probabilistic design of optimal sequential decision-making algorithms in learning and control
This survey is focused on certain sequential decision-making problems that involve
optimizing over probability functions. We discuss the relevance of these problems for …
optimizing over probability functions. We discuss the relevance of these problems for …
Aligning robot and human representations
To act in the world, robots rely on a representation of salient task aspects: for example, to
carry a coffee mug, a robot may consider movement efficiency or mug orientation in its …
carry a coffee mug, a robot may consider movement efficiency or mug orientation in its …
Lower bounds and accelerated algorithms for bilevel optimization
Y Liang - Journal of machine learning research, 2023 - jmlr.org
Bilevel optimization has recently attracted growing interests due to its wide applications in
modern machine learning problems. Although recent studies have characterized the …
modern machine learning problems. Although recent studies have characterized the …
Trail: Near-optimal imitation learning with suboptimal data
The aim in imitation learning is to learn effective policies by utilizing near-optimal expert
demonstrations. However, high-quality demonstrations from human experts can be …
demonstrations. However, high-quality demonstrations from human experts can be …