Papers Bilevel Optimization
“Bilevel Optimization” 태그가 달린 논문 544편 · 필터 해제
SGHA: A Single-Loop Fully First-Order Algorithm for Nonconvex-Strongly-Convex Bilevel Optimization
In this work, we study the oracle complexity of finding an $ε$-stationary point for nonconvex-strongly-convex (NC-SC) bilevel optimization using only first-order oracles. Existing methods achieving the best-known complex…
Bilevel OptimizationDesigning Compact Neural Architectures via Neuron Gating and Mixed Activation
Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters usin…
Neural Architecture SearchBilevel OptimizationFrom Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising solution, existing policies rely on local…
Bilevel OptimizationImage GenerationEfficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level
Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works have been begun to study the multi-objective bilevel optimiz…
Neural Architecture SearchBilevel OptimizationSharper Analysis of Single-Loop Methods for Bilevel Optimization
Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have adva…
Hyperparameter OptimizationNeural Architecture SearchReinforcement LearningBilevel OptimizationFunctional Bilevel Optimization for Predictive Fairness
When sensitive attributes are continuous and high-dimensional $-$ demographic score vectors, posteriors over attributes, age or income profiles $-$ enforcing full statistical independence is often too restrictive, and ex…
Bilevel OptimizationHeterogeneous Graph Condensation via Role-Aware Clustering
Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains comput…
Bilevel OptimizationBilevel Optimization for Neural Architecture Search
Bilevel optimization has become an influential and widely adopted framework for addressing hierarchical optimization problems in machine learning, providing an effective approach to modeling the interaction between two l…
Hyperparameter OptimizationNeural Architecture SearchBilevel OptimizationAgentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems
Network operators' changing policies, service requirements, and stringent real-time constraints render existing methods designed with fixed objectives and constraints ineffective. This paper presents Agentic long-term pe…
Bilevel OptimizationConstrained Variable Projection for Structured Problems
Variable projection is a classical technique for separable nonlinear least-squares problems, in which variables that enter linearly are eliminated exactly, yielding a reduced nonlinear problem. By expressing this framewo…
Bilevel OptimizationFew-Shot LearningEscaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization
Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally stochastic root-finding problems rather than loss minimization. Yet, …
Reinforcement LearningBilevel OptimizationDistribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation
Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Existing variance-reduction techniques typically rely on myopic magnitu…
Reinforcement LearningBilevel OptimizationDUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server. However, most existing DBO met…
Bilevel OptimizationFederated Bilevel Performative Prediction
Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and communication constraints. Most existing …
Bilevel OptimizationStealthy World Model Manipulation via Data Poisoning
Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time …
Bilevel OptimizationEvolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning
Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this…
Reinforcement LearningBilevel OptimizationContinuous ControlLiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers
This paper proposes a Linear Programming (LP)-based local search framework for fine-tuning pretrained transformer models with explicit control against overfitting. The approach formulates transformer fine-tuning as a bil…
Bilevel OptimizationFastMix: Fast Data Mixture Optimization via Gradient Descent
While large and diverse datasets have driven recent advances in large models, identifying the optimal data mixture for pre-training and post-training remains a significant open problem. We address this challenge with FAS…
Bilevel OptimizationMixed-Categorical Black-Box Optimization via Information-Geometric Bilevel Decomposition
Mixed categorical-continuous optimization arises in many practical domains, yet remains challenging. In the black-box setting, evolution strategy-based approaches have shown promise in extending the efficiency and robust…
Bilevel OptimizationGradient based Bilevel for Inverse Optimal Control, a Riemannian approach
Inverse Optimal Control (IOC) aims to recover the cost function that explains observed trajectories as solutions of an optimal control problem. Classical IOC formulations rely on bilevel optimization, which repeatedly so…
Bilevel Optimization