ICML 2024 Papers

As a well-known machine learning algorithm, sparse Bayesian learning (SBL) can find sparse representations in linearly probabilistic models by imposing a sparsity-promoting prior on model coefficients. However, classical SBL algorithms lack the essential theoretical guarantees of global convergence. To address this issue, we propose an iterative Min-Min optimization method to solve the marginal likelihood function (MLF) of SBL based on the concave-convex procedure. The method can optimize the hyperparameters related to both the prior and noise level analytically at each iteration by re-expressing MLF using auxiliary functions. Particularly, we demonstrate that the method globally converges to a local minimum or saddle point of MLF. With rigorous theoretical guarantees, the proposed novel SBL algorithm outperforms classical ones in finding sparse representations on simulation and real-world examples, ranging from sparse signal recovery to system identification and kernel regression.

The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with minimal deviation from the initial policy. While considered as a straightforward solution, reinforcement learning (RL) suffers from high variance in policy updates, which impedes efficient policy improvement. Recently, direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. However, we show that DPO derived based on the optimal solution of the problem leads to a compromised mean-seeking approximation of the optimal solution in practice. In this paper, we propose efficient exact optimization (EXO) of the alignment objective. EXO is guaranteed to optimize in the same direction as RL algorithms asymptotically for arbitrary policy parametrization. This leads to the same mode-seeking solution, while enables efficient optimization by circumventing the complexities of RL. We also compare our method to DPO with both theoretical and empirical analyses, and further demonstrate the advantages of our method over existing approaches on realistic human preference data. Code is available at https://github.com/haozheji/exact-optimization.

Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to efficiently locate favorable minima in deep neural networks. This efficiency, however, contrasts with the non-convex and seemingly complex structure of neural loss landscapes. In this study, we delve into the fundamental geometric properties of sampled gradients along optimization paths. We focus on two key quantities, the restricted secant inequality and error bound, as well as their ratio γ, which hold high significance for first-order optimization. Our analysis reveals that these quantities exhibit predictable, consistent behavior throughout training, despite the stochasticity induced by sampling minibatches. Our findings suggest that not only do optimization trajectories never encounter significant obstacles, but they also maintain stable dynamics during the majority of training. These observed properties are sufficiently expressive to theoretically guarantee linear convergence and prescribe learning rate schedules mirroring empirical practices. We conduct our experiments on image classification, semantic segmentation and language modeling across different batch sizes, network architectures, datasets, optimizers, and initialization seeds. We discuss the impact of each factor. Our work provides novel insights into the properties of neural network loss functions, and opens the door to theoretical frameworks more relevant to prevalent practice.

An open problem in differentially private deep learning is hyperparameter optimization (HPO). DP-SGD introduces new hyperparameters and complicates existing ones, forcing researchers to painstakingly tune hyperparameters with hundreds of trials, which in turn makes it impossible to account for the privacy cost of HPO without destroying the utility. We propose an adaptive HPO method that uses cheap trials (in terms of privacy cost and runtime) to estimate optimal hyperparameters and scales them up. We obtain state-of-the-art performance on 22 benchmark tasks, across computer vision and natural language processing, across pretraining and finetuning, across architectures and a wide range of $\varepsilon \in [0.01,8.0]$, all while accounting for the privacy cost of HPO.

Stochastic bilevel optimization tackles challenges involving nested optimization structures. Its fast-growing scale nowadays necessitates efficient distributed algorithms. In conventional distributed bilevel methods, each worker must transmit full-dimensional stochastic gradients to the server every iteration, leading to significant communication overhead and thus hindering efficiency and scalability. To resolve this issue, we introduce the **first** family of distributed bilevel algorithms with communication compression. The primary challenge in algorithmic development is mitigating bias in hypergradient estimation caused by the nested structure. We first propose C-SOBA, a simple yet effective approach with unbiased compression and provable linear speedup convergence. However, it relies on strong assumptions on bounded gradients. To address this limitation, we explore the use of moving average, error feedback, and multi-step compression in bilevel optimization, resulting in a series of advanced algorithms with relaxed assumptions and improved convergence properties. Numerical experiments show that our compressed bilevel algorithms can achieve $10\times$ reduction in communication overhead without severe performance degradation.

Moderate-sized large language models (LLMs) -- those with 7B or 13B parameters -- exhibit promising machine translation (MT) performance. However, they do not match the performance of state-of-the-art conventional encoder-decoder translation models or larger-scale LLMs such as GPT-4. In this study, we bridge this performance gap. We first assess the shortcomings of supervised fine-tuning for LLMs in the MT task, emphasizing the quality issues present in the reference data, despite being human-generated. Then, in contrast to supervised fine-tuning which mimics reference translations, we introduce Contrastive Preference Optimization (CPO), a novel approach that trains models to avoid generating adequate but not perfect translations. Applying CPO to ALMA models with only 22K parallel sentences and 0.1% parameters yields significant improvements. The resulting model, called ALMA-R, can match or exceed the performance of the WMT competition winners and GPT-4 on WMT'21, WMT'22 and WMT'23 test datasets.

We leverage multilevel Monte Carlo (MLMC) to improve the performance of multi-step look- ahead Bayesian optimization (BO) methods that involve nested expectations and maximizations. Often these expectations must be computed by Monte Carlo (MC). The complexity rate of naive MC degrades for nested operations, whereas MLMC is capable of achieving the canonical MC convergence rate for this type of problem, independently of dimension and without any smoothness assumptions. Our theoretical study focuses on the approximation improvements for two- and three-step look-ahead acquisition functions, but, as we discuss, the approach is generalizable in various ways, including beyond the context of BO. Our findings are verified numerically and the benefits of MLMC for BO are illustrated on several benchmark examples. Code is available at https://github.com/Shangda-Yang/MLMCBO.

Bayesian optimization (BO) is a popular method to optimize costly black-box functions, and meta-learning has emerged as a way to leverage knowledge from related tasks to optimize new tasks faster. However, existing meta-learning methods for BO rely on surrogate models that are not scalable or are sensitive to varying input scales and noise types across tasks. Moreover, they often overlook the uncertainty associated with task similarity, leading to unreliable task adaptation when a new task differs significantly or has not been sufficiently explored yet. We propose a novel meta-learning BO approach that bypasses the surrogate model and directly learns the utility of queries across tasks. It explicitly models task uncertainty and includes an auxiliary model to enable robust adaptation to new tasks. Extensive experiments show that our method achieves strong performance and outperforms multiple meta-learning BO methods across various benchmarks.

Offline optimization aims to maximize a black-box objective function with a static dataset and has wide applications. In addition to the objective function being black-box and expensive to evaluate, numerous complex real-world problems entail optimizing multiple conflicting objectives, i.e., multi-objective optimization (MOO). Nevertheless, offline MOO has not progressed as much as offline single-objective optimization (SOO), mainly due to the lack of benchmarks like Design-Bench for SOO. To bridge this gap, we propose a first benchmark for offline MOO, covering a range of problems from synthetic to real-world tasks. This benchmark provides tasks, datasets, and open-source examples, which can serve as a foundation for method comparisons and advancements in offline MOO. Furthermore, we analyze how the current related methods can be adapted to offline MOO from four fundamental perspectives, including data, model architecture, learning algorithm, and search algorithm. Empirical results show improvements over the best value of the training set, demonstrating the effectiveness of offline MOO methods. As no particular method stands out significantly, there is still an open challenge in further enhancing the effectiveness of offline MOO. We finally discuss future challenges for offline MOO, with the hope of shedding some light on this emerging field. Our code is available at https://github.com/lamda-bbo/offline-moo.

This paper studies the problem of stochastic bilevel optimization where the upper-level function is nonconvex with potentially unbounded smoothness and the lower-level function is strongly convex. This problem is motivated by meta-learning applied to sequential data, such as text classification using recurrent neural networks, where the smoothness constant of the upper-level loss function scales linearly with the gradient norm and can be potentially unbounded. Existing algorithm crucially relies on the nested loop design, which requires significant tuning efforts and is not practical. In this paper, we address this issue by proposing a Single Loop bIlevel oPtimizer (SLIP). The proposed algorithm first updates the lower-level variable by a few steps of stochastic gradient descent, and then simultaneously updates the upper-level variable by normalized stochastic gradient descent with momentum and the lower-level variable by stochastic gradient descent. Under standard assumptions, we show that our algorithm finds an $\epsilon$-stationary point within $\widetilde{O}(1/\epsilon^4)$[Here $\widetilde{O}(\cdot)$ compresses logarithmic factors of $1/\epsilon$ and $1/\delta$, where $\delta\in(0,1)$ denotes the failure probability.] oracle calls of stochastic gradient or Hessian-vector product, both in expectation and with high probability. This complexity result is nearly optimal up to logarithmic factors without mean-square smoothness of the stochastic gradient oracle. Our proof relies on (i) a refined characterization and control of the lower-level variable and (ii) establishing a novel connection between bilevel optimization and stochastic optimization under distributional drift. Our experiments on various tasks show that our algorithm significantly outperforms strong baselines in bilevel optimization.

This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Existing projection-free algorithms for solving this problem suffer from two limitations: 1) they solely focus on the gradient mapping criterion and fail to match the optimal sample complexities in unconstrained settings; 2) their analysis is exclusively applicable to non-convex functions, without considering convex and strongly convex objectives. To address these issues, we introduce novel projection-free variance reduction algorithms and analyze their complexities under different criteria. For gradient mapping, our complexities improve existing results and match the optimal rates for unconstrained problems. For the widely-used Frank-Wolfe gap criterion, we provide theoretical guarantees that align with those for single-level problems. Additionally, by using a stage-wise adaptation, we further obtain complexities for convex and strongly convex functions. Finally, numerical experiments on different tasks demonstrate the effectiveness of our methods.

This paper addresses a policy optimization task with the conditional value-at-risk (CVaR) objective. We introduce the *predictive CVaR policy gradient*, a novel approach that seamlessly integrates risk-neutral policy gradient algorithms with minimal modifications. Our method incorporates a reweighting strategy in gradient calculation -- individual cost terms are reweighted in proportion to their *predicted* contribution to the objective. These weights can be easily estimated through a separate learning procedure. We provide theoretical and empirical analyses, demonstrating the validity and effectiveness of our proposed method.

The stochastic proximal gradient method is a powerful generalization of the widely used stochastic gradient descent (SGD) method and has found numerous applications in Machine Learning. However, it is notoriously known that this method fails to converge in non-convex settings where the stochastic noise is significant (i.e. when only small or bounded batch sizes are used). In this paper, we focus on the stochastic proximal gradient method with Polyak momentum. We prove this method attains an optimal convergence rate for non-convex composite optimization problems, regardless of batch size. Additionally, we rigorously analyze the variance reduction effect of the Polyak momentum in the composite optimization setting and we show the method also converges when the proximal step can only be solved inexactly. Finally, we provide numerical experiments to validate our theoretical results.

We introduce a multiple target optimization framework for DP-SGD referred to as pro-active DP. In contrast to traditional DP accountants, which are used to track the expenditure of privacy budgets, the pro-active DP scheme allows one to *a-priori* select parameters of DP-SGD based on a fixed privacy budget (in terms of $\epsilon$ and $\delta$) in such a way to optimize the anticipated utility (test accuracy) the most. To achieve this objective, we first propose significant improvements to the moment account method, presenting a closed-form $(\epsilon,\delta)$-DP guarantee that connects all parameters in the DP-SGD setup. Generally, DP-SGD is $(\epsilon\leq 1/2,\delta=1/N)$-DP if $\sigma=\sqrt{2(\epsilon +\ln(1/\delta))/\epsilon}$ with $T$ at least $\approx 2k^2/\epsilon$ and $(2/e)^2k^2-1/2\geq \ln(N)$, where $T$ is the total number of rounds, and $K=kN$ is the total number of gradient computations where $k$ measures $K$ in number of epochs of size $N$ of the local data set. We prove that our expression is close to tight in that if $T$ is more than a constant factor $\approx 4$ smaller than the lower bound $\approx 2k^2/\epsilon$, then the $(\epsilon,\delta)$-DP guarantee is violated. Our enhanced DP theory allows us to create a utility graph and DP calculator. These tools link privacy and utility objectives and search for optimal experiment setups, efficiently taking into account both accuracy and privacy objectives, as well as implementation goals. We furnish a comprehensive implementation flow of our proactive DP, with rigorous experiments to showcase the proof-of-concept.

Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problems are solved via their min-max Lagrangian formulations, which exhibit unstable oscillatory dynamics when optimized using gradient descent-ascent. The adoption of constrained optimization techniques in the machine learning community is currently limited by the lack of reliable, general-purpose update schemes for the Lagrange multipliers. This paper proposes the νPI algorithm and contributes an optimization perspective on Lagrange multiplier updates based on PI controllers, extending the work of Stooke, Achiam and Abbeel (2020). We provide theoretical and empirical insights explaining the inability of momentum methods to address the shortcomings of gradient descent-ascent, and contrast this with the empirical success of our proposed νPI controller. Moreover, we prove that νPI generalizes popular momentum methods for single-objective minimization. Our experiments demonstrate that νPI reliably stabilizes the multiplier dynamics and its hyperparameters enjoy robust and predictable behavior.

While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimization. Our main result resolves this question: SPABA, an adaptation of the PAGE method for nonconvex optimization in (Li et al., 2021) to the bilevel setting, can achieve optimal sample complexity in both the finite-sum and expectation settings. We show the optimality of SPABA by proving that there is no gap in complexity analysis between stochastic bilevel and single-level optimization when implementing PAGE. Notably, as indicated by the results of (Dagréou et al., 2022), there might exist a gap in complexity analysis when implementing other stochastic gradient estimators, like SGD and SAGA. In addition to SPABA, we propose several other single-loop stochastic bilevel algorithms, that either match or improve the state-of-the-art sample complexity results, leveraging our convergence rate and complexity analysis. Numerical experiments demonstrate the superior practical performance of the proposed methods.

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the evaluation of full answers generated by the models. However, the generation of these responses occurs in a token level, following a sequential, auto-regressive fashion. In this paper, we introduce Token-level Direct Preference Optimization (TDPO), a novel approach to align LLMs with human preferences by optimizing policy at the token level. Unlike previous methods, which face challenges in divergence efficiency, TDPO integrates forward KL divergence constraints for each token, improving alignment and diversity. Utilizing the Bradley-Terry model for a token-based reward system, our method enhances the regulation of KL divergence, while preserving simplicity without the need for explicit reward modeling. Experimental results across various text tasks demonstrate TDPO’s superior performance in balancing alignment with generation diversity. Notably, fine-tuning with TDPO strikes a better balance than DPO in the controlled sentiment generation and single-turn dialogue datasets, and significantly improves the quality of generated responses compared to both DPO and PPO-based RLHF methods.

Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.

The $\ell_0$-constrained mean-CVaR model poses a significant challenge due to its NP-hard nature, typically tackled through combinatorial methods characterized by high computational demands. From a markedly different perspective, we propose an innovative autonomous sparse mean-CVaR portfolio model, capable of approximating the original $\ell_0$-constrained mean-CVaR model with arbitrary accuracy. The core idea is to convert the $\ell_0$ constraint into an indicator function and subsequently handle it through a tailed approximation. We then propose a proximal alternating linearized minimization algorithm, coupled with a nested fixed-point proximity algorithm (both convergent), to iteratively solve the model. Autonomy in sparsity refers to retaining a significant portion of assets within the selected asset pool during adjustments in pool size. Consequently, our framework offers a theoretically guaranteed approximation of the $\ell_0$-constrained mean-CVaR model, improving computational efficiency while providing a robust asset selection scheme.