REVIEW 4 cited by
A Generalized Alternating Method for Bilevel Learning under the Polyak-{L}ojasiewicz Condition
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Generalized Alternating Method for Bilevel Learning under the Polyak-{L}ojasiewicz Condition
read the original abstract
Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-{\L}ojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an $\epsilon$-stationary point for the considered problem within $\tilde{\cal O}(\epsilon^{-1})$ iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.
Forward citations
Cited by 4 Pith papers
-
Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization
SDBPG and its penalty/variance-reduced variants achieve the first explicit (ε_f, ε_g)-stationarity rates for stochastic nonconvex simple bilevel problems by regularizing unbounded dual multipliers.
-
Second-Order Bilevel Optimization with Accelerated Convergence Rates
Second-order bilevel methods achieve Õ(ε^{-1.5}) iteration complexity for second-order stationary points, faster than first-order approaches, with a lazy variant improving computational efficiency by √d.
-
Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
CMAT uses a transformer decoder to produce a high-level consensus vector in latent space, enabling simultaneous order-independent actions by all agents and optimization via single-agent PPO, with superior results on S...
-
Bilevel learning
Bilevel learning methods rely on implicit differentiation but are restricted by assumptions of unique lower-level solutions and struggle with constraints, and connections to broader bilevel optimization literature may...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.