Federated bilevel optimization (FBO) has garnered significant attention lately, driven by its promising applications in meta-learning and hyperparameter optimization. Existing algorithms generally aim to approximate the gradient of the upper-level objective function (hypergradient) in the federated setting. However, because of the nonlinearity of the hypergradient and client drift, they often involve complicated computations. These computations, like multiple optimization sub-loops and second-order derivative evaluations, end up with significant memory consumption and high computational costs. In this paper, we propose a computationally and memory-efficient FBO algorithm named MemFBO. MemFBO features a fully single-loop structure with all involved variables updated simultaneously, and uses only first-order gradient information for all local updates. We show that MemFBO exhibits a linear convergence speedup with milder assumptions in both partial and full client participation scenarios. We further implement MemFBO in a novel FBO application for federated data cleaning. Our experiments, conducted on this application and federated hyper-representation, demonstrate the effectiveness of the proposed algorithm.
论文检索
输入标题、作者或关键词，从 222 篇学术成果中精准定位
Convergence Rate in a Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence
PDF ↗The nonlinear two-time-scale stochastic approximation is widely studied under conditions of bounded variances in noise. Motivated by recent advances that allow for variability linked to the current state or time, we consider state- and time-dependent noises. We show that the Lyapunov function exhibits polynomial convergence rates in both cases, with the rate of polynomial delay depending on the parameters of state- or time-dependent noises. Notably, if the state noise parameters fully approach their limiting value, the Lyapunov function achieves an exponential convergence rate. We provide two numerical examples to illustrate our theoretical findings in the context of stochastic gradient descent with Polyak-Ruppert averaging and stochastic bilevel optimization.
This paper initiates the first exploratory study to investigate the robust integrated sensing and communication (ISAC) systems under channel estimation errors from the perspective of GPU-Accelerated bilevel optimization. Within this framework, the upper-level problem is dedicated to simultaneously optimizing communication and sensing objectives, quantified respectively by weighted sum rate and Cram\'er-Rao lower bound, while the lower-level problem considers the channel uncertainties. We then propose an efficient algorithm that can find a set of Pareto optimal solutions with different trade-offs among communication rates and sensing accuracy. The theoretical analysis regarding the convergence rate has also been provided. Furthermore, we design a bilevel optimization inspired deep neural network architecture for that can be realized efficiently on GPU platform. Experiments have been conducted to evaluate the performances of proposed methods. In particular, the proposed GPU-accelerated parallel bilevel optimization can accelerate the convergence speed by up to 50 times compared to conventional gradient-based methods. This characteristic renders it especially suitable for real-time applications, exemplified by the demanding requirements of robust ISAC in upcoming 6G networks.
In this paper, we explore a novel image matting task aimed at achieving efficient inference under various computational cost constraints, specifically FLOP limitations, using a single matting network. Existing matting methods which have not explored scalable architectures or path-learning strategies, fail to tackle this challenge. To overcome these limitations, we introduce Path-Adaptive Matting (PAM), a framework that dynamically adjusts network paths based on image contexts and computational cost constraints. We formulate the training of the computational cost-constrained matting network as a bilevel optimization problem, jointly optimizing the matting network and the path estimator. Building on this formalization, we design a path-adaptive matting architecture by incorporating path selection layers and learnable connect layers to estimate optimal paths and perform efficient inference within a unified network. Furthermore, we propose a performance-aware path-learning strategy to generate path labels online by evaluating a few paths sampled from the prior distribution of optimal paths and network estimations, enabling robust and efficient online path learning. Experiments on five image matting datasets demonstrate that the proposed PAM framework achieves competitive performance across a range of computational cost constraints.
Recent advances in diffusion generative models have yielded remarkable progress. While the quality of generated content continues to improve, these models have grown considerably in size and complexity. This increasing computational burden poses significant challenges, particularly in resource-constrained deployment scenarios such as mobile devices. The combination of model pruning and knowledge distillation has emerged as a promising solution to reduce computational demands while preserving generation quality. However, this technique inadvertently propagates undesirable behaviors, including the generation of copyrighted content and unsafe concepts, even when such instances are absent from the fine-tuning dataset. In this paper, we propose a novel bilevel optimization framework for pruned diffusion models that consolidates the fine-tuning and unlearning processes into a unified phase. Our approach maintains the principal advantages of distillation--namely, efficient convergence and style transfer capabilities--while selectively suppressing the generation of unwanted content. This plug-in framework is compatible with various pruning and concept unlearning methods, facilitating efficient, safe deployment of diffusion models in controlled environments.
Aligning large language models (LLMs) with human preferences relies heavily on high-quality reward models. However, existing approaches struggle with two critical challenges: noisy preference labels and the varying importance of preference samples. We introduce DORM, a method that enhances reward modeling by learning to dynamically weigh preference data.DORM initializes data importance using a combination of model uncertainty and prediction disagreement, then iteratively refines them via bilevel optimization to maximize validation performance. Using only 50k samples, DORM trains a 12B reward model that achieves 90.5% accuracy on RewardBench, matching the performance of models trained on significantly larger datasets. Furthermore, downstream alignment tasks show that fine-tuned LLMs with DORM achieve a 61.2% win rate against baseline methods, highlighting its data efficiency and generalizability.
GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
PDF ↗Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by the small number of trainable parameters. Recent work combines LoRA with the Mixture-of-Experts (MoE), i.e., LoRA-MoE, to enhance capacity, but two limitations remain in hindering the full exploitation of its potential: 1) the influence of downstream tasks when assigning expert numbers, and 2) the uniform rank assignment across all LoRA experts, which restricts representational diversity.To mitigate these gaps, we propose GuiLoMo, a fine-grained layer-wise expert numbers and ranks allocation strategy with GuidedSelection Vectors (GSVs). GSVs are learned via a prior bilevel optimization process to capture both model- and task-specific needs, and are then used to allocate optimal expert numbers and ranks.Experiments on three backbone models across diverse benchmarks show that GuiLoMo consistently achieves superior or comparable performance to all baselines. Further analysis offers key insights into how expert numbers and ranks vary across layers and tasks, highlighting the benefits of adaptive expert configuration. Our code is available at https://anonymous.4open.science/r/GuiLoMo-034.
Optimization
Decentralized bilevel optimization has garnered significant attention due to its critical role in solving large-scale machine learning problems. However, existing methods often rely on prior knowledge of problem parameters—such as smoothness, convexity, or communication network topologies—to determine appropriate stepsizes. In practice, these problem parameters are typically unavailable, leading to substantial manual effort for hyperparameter tuning. In this paper, we propose \textbf{AdaSDBO}, a fully problem-parameter-free algorithm for decentralized bilevel optimization with a single-loop structure. AdaSDBO leverages adaptive stepsizes based on cumulative gradient norms to update all variables simultaneously, dynamically adjusting its progress and eliminating the need for problem-specific hyperparameter tuning. Through rigorous theoretical analysis, we establish that AdaSDBO achieves a convergence rate of $\widetilde{\mathcal{O}}\left(\frac{1}{T}\right)$, matching the performance of well-tuned state-of-the-art methods up to polylogarithmic factors. Extensive numerical experiments demonstrate that AdaSDBO delivers competitive performance compared to existing decentralized bilevel optimization methods while exhibiting remarkable robustness across diverse stepsize configurations.
Optimization · Neural Network Optimization
Sparse and low-rank matrix composite approximation has emerged as a promising paradigm for compressing large language models (LLMs), offering a more flexible pruning structure than conventional methods based solely on sparse matrices. The significant variation in weight redundancy across layers, along with the differing rank and sparsity structures of weight matrices, makes identifying the globally optimal pruning structure extremely challenging. Existing methods often depend on uniform or manually designed heuristic rules to allocate weight sparsity across layers, subsequently compressing each matrix using matrix approximation techniques. Given the above theoretical difficulty in global compression of LLMs and the limited computational and data resources available compared to the training phase, we argue that a collaboration between learning and matrix approximation is essential for effective compression. In this paper, we propose a novel LLM compression framework based on generalized bilevel optimization that naturally formulates an effective collaborative mechanism. Specifically, the outer loop frames the weight allocation task as a probabilistic optimization problem, enabling the automatic learning of both layer-wise sparsities and matrix-wise retained ranks, while the inner loop solves the corresponding sparsity and rank-constrained model compression problem via matrix approximation. Our main technical contributions include two key innovations for efficiently solving this bilevel optimization problem. First, we introduce a truncated Gaussian prior-based probabilistic parameterization integrated with a policy gradient estimator, which avoids expensive backpropagation and stabilizes the optimization process. Second, we design an adapted QR-based matrix approximation algorithm that significantly accelerates inner loop computations. Extensive experiments on Phi-3 and the LLama-2/3 family demonstrate the effectiveness of our method. Notably, it maintains over 95\% zero-shot accuracy under 50\% sparsity and achieves up to 2× inference speedup.
Social Aspects · Fairness, Equity, Justice and Safety
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to lightweight student models. While teacher models from third-party platforms may undergo security verification (e.g., backdoor detection), we uncover a novel and critical threat: distillation-conditional backdoor attacks (DCBAs). DCBA injects dormant and undetectable backdoors into teacher models, which become activated in student models via the KD process, even with clean distillation datasets. While the direct extension of existing methods is ineffective for DCBA, we implement this attack by formulating it as a bilevel optimization problem and proposing a simple yet effective method (i.e., SCAR). Specifically, the inner optimization simulates the KD process by optimizing a surrogate student model, while the outer optimization leverages outputs from this surrogate to optimize the teacher model for implanting the conditional backdoor. Our SCAR addresses this complex optimization utilizing an implicit differentiation algorithm with a pre-optimized trigger injection function. Extensive experiments across diverse datasets, model architectures, and KD techniques validate the effectiveness of our SCAR and its resistance against existing backdoor detection, highlighting a significant yet previously overlooked vulnerability in the KD process. Our code is available at https://github.com/WhitolfChen/SCAR.
Deep Learning · Algorithms
Data selection improves computational efficiency by choosing informative subsets of training samples. However, existing methods ignore the compute budget, treating data selection and importance evaluation independently of compute budget constraints. Yet empirical studies show no algorithm can consistently outperform others (or even random selection) across varying budgets. We therefore argue that compute budget must be integral to data-selection strategies, since different budgets impose distinct requirements on data quantity, quality, and distribution for effective training. To this end, we propose a novel Computational budget-Aware Data Selection (CADS) method and naturally formulate it into a bilevel optimization framework, where the inner loop trains the model within the constraints of the computational budget on some selected subset of training data, while the outer loop optimizes data selection based on model evaluation. Our technical contributions lie in addressing two main challenges in solving this bilevel optimization problem: the expensive Hessian matrix estimation for outer-loop gradients and the computational burden of achieving inner-loop optimality during iterations. To solve the first issue, we propose a probabilistic reparameterization strategy and compute the gradient using a Hessian-free policy gradient estimator. To address the second challenge, we transform the inner optimization problem into a penalty term in the outer objective, further discovering that we only need to estimate the minimum of a one-dimensional loss to calculate the gradient, significantly improving efficiency. To accommodate different data selection granularities, we present two complementary CADS variants: an example-level version (CADS-E) offering fine-grained control and a source-level version (CADS-S) aggregating samples into source groups for scalable, efficient selection without sacrificing effectiveness. Extensive experiments show that our method achieves performance gains of up to 14.42\% over baselines in vision and language benchmarks. Additionally, CADS achieves a 3-20× speedup compared to conventional bilevel implementations, with acceleration correlating positively with compute budget size.
Theory · Learning Theory
Bilevel optimization has emerged as a technique for addressing a wide range of machine learning problems that involve an outer objective implicitly determined by the minimizer of an inner problem. While prior works have primarily focused on the parametric setting, a learning-theoretic foundation for bilevel optimization in the nonparametric case remains relatively unexplored. In this paper, we take a first step toward bridging this gap by studying Kernel Bilevel Optimization (KBO), where the inner objective is optimized over a reproducing kernel Hilbert space. This setting enables rich function approximation while providing a foundation for rigorous theoretical analysis. In this context, we derive novel finite-sample generalization bounds for KBO, leveraging tools from empirical process theory. These bounds further allow us to assess the statistical accuracy of gradient-based methods applied to the empirical discretization of KBO. We numerically illustrate our theoretical findings on a synthetic instrumental variable regression task.
Optimization
Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current OBO approaches rely on deterministic \textit{window-smoothed} regret minimization, which may not accurately reflect system performance when functions change rapidly. In this work, we introduce a novel search direction and show that both first- and zeroth-order (ZO) stochastic OBO algorithms leveraging this direction achieve sublinear {stochastic bilevel regret without window smoothing}. Beyond these guarantees, our framework enhances efficiency by: (i) reducing oracle dependence in hypergradient estimation, (ii) updating inner and outer variables alongside the linear system solution, and (iii) employing ZO-based estimation of Hessians, Jacobians, and gradients. Experiments on online parametric loss tuning and black-box adversarial attacks validate our approach.
As the economic and environmental costs of training and deploying large vision or language models increase dramatically, analog in-memory computing (AIMC) emerges as a promising energy-efficient solution. However, the training perspective, especially its training dynamic, is underexplored. In AIMC hardware, the trainable weights are represented by the conductance of resistive elements and updated using consecutive electrical pulses. While the conductance changes by a constant in response to each pulse, in reality, the change is scaled by asymmetric and non-linear response functions, leading to a non-ideal training dynamic. This paper provides a theoretical foundation for gradient-based training on AIMC hardware with non-ideal response functions. We demonstrate that asymmetric response functions negatively impact Analog SGD by imposing an implicit penalty on the objective. To overcome the issue, we propose residual learning algorithm, which provably converges exactly to a critical point by solving a bilevel optimization problem. We show that the proposed method can be extended to deal with other hardware imperfections like limited response granularity. As far as we know, it is the first paper to investigate the impact of a class of generic non-ideal response functions. The conclusion is supported by simulations validating our theoretical insights.
Optimization
Bilevel optimization, a hierarchical optimization paradigm, has gained significant attention in a wide range of practical applications, notably in the fine-tuning of generative models. However, due to the nested problem structure, most existing algorithms require either the Hessian vector calculation or the nested loop updates, which are computationally inefficient in large language model (LLM) fine-tuning. In this paper, building upon the fully first-order penalty-based approach, we propose an efficient value function-free (\textsf{PBGD-Free}) algorithm that eliminates the loop of solving the lower-level problem and admits fully single-loop updates. Inspired by the landscape analysis of representation learning-based LLM fine-tuning problem, we propose a relaxed flatness condition for the upper-level function and prove the convergence of the proposed value-function-free algorithm. We test the performance of the proposed algorithm in various applications and demonstrate its superior computational efficiency over the state-of-the-art bilevel methods.
Deep Learning · Algorithms
In real world, the observed label distribution of a dataset often mismatches its true distribution due to noisy labels. In this situation, noisy labels learning (NLL) methods directly integrated with long-tail learning (LTL) methods tend to fail due to a dilemma: NLL methods normally rely on unbiased model predictions to recover true distribution by selecting and correcting noisy labels; while LTL methods like logit adjustment depends on true distributions to adjust biased predictions, leading to a deadlock of mutual dependency defined in this paper. To address this, we propose \texttt{Unlocker}, a bilevel optimization framework that integrates NLL methods and LTL methods to iteratively disentangle this deadlock. The inner optimization leverages NLL to train the model, incorporating LTL methods to fairly select and correct noisy labels. The outer optimization adaptively determines an adjustment strength, mitigating model bias from over- or under-adjustment. We also theoretically prove that this bilevel optimization problem is convergent by transferring the outer optimization target to an equivalent problem with a closed-form solution. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness of our method in alleviating model bias and handling long-tailed noisy label data. Code is available at \url{https://anonymous.4open.science/r/neurips-2025-anonymous-1015/}.
Optimization
Bilevel optimization has garnered significant attention in the machine learning community recently, particularly regarding the development of efficient numerical methods. While substantial progress has been made in developing efficient algorithms for optimistic bilevel optimization, the study of methods for solving Pessimistic Bilevel Optimization (PBO) remains relatively less explored, especially the design of fully first-order, single-loop gradient-based algorithms. This paper aims to bridge this research gap. We first propose a novel smooth approximation to the PBO problem, using penalization and regularization techniques. Building upon this approximation, we then propose SiPBA (Single-loop Pessimistic Bilevel Algorithm), a new gradient-based method specifically designed for PBO which avoids second-order derivative information or inner-loop iterations for subproblem solving. We provide theoretical validation for the proposed smooth approximation scheme and establish theoretical convergence for the algorithm SiPBA. Numerical experiments on synthetic examples and practical applications demonstrate the effectiveness and efficiency of SiPBA.
Deep Learning · Algorithms
Fine-tuning pre-trained Large Language Models (LLMs) for downstream tasks using First-Order (FO) optimizers presents significant computational challenges. Parameter-Efficient Fine-Tuning~(PEFT) methods have been proposed to address these challenges by freezing most model parameters and training only a small subset. While PEFT is efficient, it may not outperform full fine-tuning when high task-specific performance is required. Zeroth-Order (ZO) methods offer an alternative for fine-tuning the entire pre-trained model by approximating gradients using only the forward pass, thus eliminating the computational burden of back-propagation, % in first-order methods, but they converge painfully slowly and are very sensitive to the choice of task prompts. We bridge these worlds with Bilevel‑ZOFO, a penalty‑based bilevel formulation that treats adapter parameters as a lower‑level learner coupled to an upper‑level ZO optimizer of the full backbone. This double-loop optimization strategy only requires the gradient of the PEFT model and the forward pass of the base model. We provide theoretical convergence guarantees for Bilevel ZOFO. Empirically, we demonstrate that Bilevel-ZOFO significantly outperforms existing ZO methods, achieves 2–4$\times$ faster training, and reduces sensitivity to prompts. Bilevel-ZOFO also outperforms FO PEFT methods while maintaining similar memory efficiency. Additionally, we show its strong potential for meta learning.
Optimization
In this paper, we study the problem of solving a simple bilevel optimization problem, where the upper-level objective is minimized over the solution set of the lower-level problem. We focus on the general setting in which both the upper- and lower-level objectives are smooth but potentially nonconvex. Due to the absence of additional structural assumptions for the lower-level objective—such as convexity or the Polyak–Łojasiewicz (PL) condition—guaranteeing global optimality is generally intractable. Instead, we introduce a suitable notion of stationarity for this class of problems and aim to design a first-order algorithm that finds such stationary points in polynomial time. Intuitively, stationarity in this setting means the upper-level objective cannot be substantially improved locally without causing a larger deterioration in the lower-level objective. To this end, we show that a simple and implementable variant of the dynamic barrier gradient descent (DBGD) framework can effectively solve the considered nonconvex simple bilevel problems up to stationarity. Specifically, to reach an $(\epsilon_f, \epsilon_g)$-stationary point—where $\epsilon_f$ and $\epsilon_g$ denote the target stationarity accuracies for the upper- and lower-level objectives, respectively—the considered method achieves a complexity of $\mathcal{O}(\max(\epsilon_f^{-\frac{3+p}{1+p}}, \epsilon_g^{-\frac{3+p}{2}}))$, where $p \geq 0$ is an arbitrary constant balancing the terms. To the best of our knowledge, this is the first complexity result for a discrete-time algorithm that guarantees joint stationarity for both levels in general nonconvex simple bilevel problems.
Optimization · Stochastic & Convex Optimization
We propose efficient methods for solving stochastic simple bilevel optimization problems with convex inner levels, where the goal is to minimize an outer stochastic objective function subject to the solution set of an inner stochastic optimization problem. Existing methods often rely on costly projection or linear optimization oracles over complex sets, limiting their scalability. To overcome this, we propose an iteratively regularized conditional gradient approach that leverages linear optimization oracles exclusively over the base feasible set. Our proposed methods employ a vanishing regularization sequence that progressively emphasizes the inner problem while biasing towards desirable minimal outer objective solutions. In the one-sample stochastic setting and under standard convexity assumptions, we establish non-asymptotic convergence rates of $O(t^{-1/4})$ for both the outer and inner objectives. In the finite-sum setting with a mini-batch scheme, the corresponding rates become $O(t^{-1/2})$. When the outer objective is nonconvex, we prove non-asymptotic convergence rates of $O(t^{-1/7})$ for both the outer and inner objectives in the one-sample stochastic setting, and $O(t^{-1/4})$ in the finite-sum setting. Experimental results on over-parametrized regression and dictionary learning tasks demonstrate the practical advantages of our approach over existing methods, confirming our theoretical findings.