More Like this

1. Extended Convex Lifting for Policy Optimization of Optimal and Robust Control

   Zheng, Yang; Pai, Chih-Fan; Tang, Yujie (June 2025, Proceedings of Machine Learning Research)

   Ozay, Necmiye; Balzano, Laura; Panagou, Dimitra; Abate, Alessandro (Ed.)

   Many optimal and robust control problems are nonconvex and potentially nonsmooth in their policy optimization forms. In this paper, we introduce the Extended Convex Lifting (ECL) framework, which reveals hidden convexity in classical optimal and robust control problems from a modern optimization perspective. Our ECL framework offers a bridge between nonconvex policy optimization and convex reformulations. Despite non-convexity and non-smoothness, the existence of an ECL for policy optimization not only reveals that the policy optimization problem is equivalent to a convex problem, but also certifies a class of first-order non-degenerate stationary points to be globally optimal. We further show that this ECL framework encompasses many benchmark control problems, including LQR, state-feedback and output-feedback H-infinity robust control. We believe that ECL will also be of independent interest for analyzing nonconvex problems beyond control. 

   more » « less
2. The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares

   Ge, Rong; Kakade, Sham M.; Kidambi, Rahul; Netrapalli, Praneeth (January 2019, Advances in neural information processing systems)

   Minimax optimal convergence rates for classes of stochastic convex optimization problems are well characterized, where the majority of results utilize iterate averaged stochastic gradient descent (SGD) with polynomially decaying step sizes. In contrast, SGD's final iterate behavior has received much less attention despite their widespread use in practice. Motivated by this observation, this work provides a detailed study of the following question: what rate is achievable using the final iterate of SGD for the streaming least squares regression problem with and without strong convexity? First, this work shows that even if the time horizon T (i.e. the number of iterations SGD is run for) is known in advance, SGD's final iterate behavior with any polynomially decaying learning rate scheme is highly sub-optimal compared to the minimax rate (by a condition number factor in the strongly convex case and a factor of T‾‾√ in the non-strongly convex case). In contrast, this paper shows that Step Decay schedules, which cut the learning rate by a constant factor every constant number of epochs (i.e., the learning rate decays geometrically) offers significant improvements over any polynomially decaying step sizes. In particular, the final iterate behavior with a step decay schedule is off the minimax rate by only log factors (in the condition number for strongly convex case, and in T for the non-strongly convex case). Finally, in stark contrast to the known horizon case, this paper shows that the anytime (i.e. the limiting) behavior of SGD's final iterate is poor (in that it queries iterates with highly sub-optimal function value infinitely often, i.e. in a limsup sense) irrespective of the stepsizes employed. These results demonstrate the subtlety in establishing optimal learning rate schemes (for the final iterate) for stochastic gradient procedures in fixed time horizon settings. 

   more » « less
3. Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization

   https://doi.org/10.1609/aaai.v38i8.28662  

   Zhang, Qi; Zhou, Yi; Prater-Bennette, Ashley; Shen, Lixin; Zou, Shaofeng (March 2024, Proceedings of the AAAI Conference on Artificial Intelligence)

   Distributionally robust optimization (DRO) is a powerful framework for training robust models against data distribution shifts. This paper focuses on constrained DRO, which has an explicit characterization of the robustness level. Existing studies on constrained DRO mostly focus on convex loss function, and exclude the practical and challenging case with non-convex loss function, e.g., neural network. This paper develops a stochastic algorithm and its performance analysis for non-convex constrained DRO. The computational complexity of our stochastic algorithm at each iteration is independent of the overall dataset size, and thus is suitable for large-scale applications. We focus on the general Cressie-Read family divergence defined uncertainty set which includes chi^2-divergences as a special case. We prove that our algorithm finds an epsilon-stationary point with an improved computational complexity than existing methods. Our method also applies to the smoothed conditional value at risk (CVaR) DRO. 

   more » « less
4. The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares

   Ge, Rong; Kakade, Sham M.; Kidambi, Rahul; Netrapalli, Praneeth (December 2019, NeurIPS2019)

   Minimax optimal convergence rates for numerous classes of stochastic convex optimization problems are well characterized, where the majority of results utilize iterate averaged stochastic gradient descent (SGD) with polynomially decaying step sizes. In contrast, the behavior of SGDs final iterate has received much less attention despite the widespread use in practice. Motivated by this observation, this work provides a detailed study of the following question: what rate is achievable using the final iterate of SGD for the streaming least quares regression problem with and without strong convexity? First, this work shows that even if the time horizon T (i.e. the number of iterations that SGD is run for) is known in advance, the behavior of SGDs final iterate with any polynomially decaying learning rate scheme is highly suboptimal compared to the statistical minimax rate (by a condition number factor in the strongly convex case and a factor of \sqrt{T} in the non-strongly convex case). In contrast, this paper shows that Step Decay schedules, which cut the learning rate by a constant factor every constant number of epochs (i.e., the learning rate decays geometrically) offer significant improvements over any polynomially decaying step size schedule. In particular, the behavior of the final iterate with step decay schedules is off from the statistical minimax rate by only log factors (in the condition number for the strongly convex case, and in T in the non-strongly convex case). Finally, in stark contrast to the known horizon case, this paper shows that the anytime (i.e. the limiting) behavior of SGDs final iterate is poor (in that it queries iterates with highly sub-optimal function value infinitely often, i.e. in a limsup sense) irrespective of the step size scheme employed. These results demonstrate the subtlety in establishing optimal learning rate schedules (for the final iterate) for stochastic gradient procedures in fixed time horizon settings. 

   more » « less
5. Extracting Dual Solutions via Primal Optimizers

   https://doi.org/10.4230/LIPICS.ITCS.2025.29  

   Carmon, Yair; Jambulapati, Arun; O'Carroll, Liam; Sidford, Aaron (January 2025, Schloss Dagstuhl – Leibniz-Zentrum für Informatik)

   Meka, Raghu (Ed.)

   We provide a general method to convert a "primal" black-box algorithm for solving regularized convex-concave minimax optimization problems into an algorithm for solving the associated dual maximin optimization problem. Our method adds recursive regularization over a logarithmic number of rounds where each round consists of an approximate regularized primal optimization followed by the computation of a dual best response. We apply this result to obtain new state-of-the-art runtimes for solving matrix games in specific parameter regimes, obtain improved query complexity for solving the dual of the CVaR distributionally robust optimization (DRO) problem, and recover the optimal query complexity for finding a stationary point of a convex function. 

   more » « less