Differentiable Optimization

Overview

Differentiable optimization studies how to compute gradients through iterative algorithms and constrained decisions so their parameters or inputs can be learned end to end. Common approaches unroll solver iterations, use implicit differentiation or adjoints, or build differentiable layers from projections, quadratic programs, and conic solvers. These methods support tasks such as hyperparameter tuning, decision-focused prediction, robotics control, and physics-based design, where improving the final decision matters as much as improving a prediction. A central challenge is balancing scalable, reliable gradients with exact feasibility and discrete or nonsmooth decisions, especially in large or numerically sensitive problems.

Latest papers

93 papers10 papers in the last four weeks, up 25% on the four weeks before. 0.1% of all new papers.

Sep 2, 2025

Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport

The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gaussian Mixture Models (GMMs). Despite its ubiquity, EM is typically treated as a non-differentiable black box, preventing its integration into modern learning pipelines where end-to-end gradient propagation is essential. In this work, we present and compare several differentiation strategies for EM, from full automatic differentiation to approximate methods, assessing their accuracy and computational efficiency. As a key application, we leverage this differentiable EM in the computation of the Mixture Wasserstein distance MW2\mathrm{MW}_2 between GMMs, allowing MW2\mathrm{MW}_2 to be used as a differentiable loss in imaging and machine learning tasks. To complement our practical use of MW2\mathrm{MW}_2, we contribute a novel stability result which provides theoretical justification for the use of MW2\mathrm{MW}_2 with EM, and also introduce a novel unbalanced variant of MW2\mathrm{MW}_2. Numerical experiments on barycentre computation, colour and style transfer, image generation, and texture synthesis illustrate the versatility of the proposed approach in different settings.
May 28, 2025

Accelerating Optimization via Differentiable Stopping Time

Optimization is an important module of modern machine learning applications. Tremendous efforts have been made to accelerate optimization algorithms. A common formulation is achieving a lower loss at a given time. This enables a differentiable framework with respect to the algorithm hyperparameters. In contrast, its dual, minimizing the time to reach a target loss, is believed to be non-differentiable, as the time is not differentiable. As a result, it usually serves as a conceptual framework or is optimized using zeroth-order methods. To address this limitation, we propose a differentiable stopping time and theoretically justify it based on differential equations. An efficient algorithm is designed to backpropagate through it. As a result, the proposed differentiable stopping time enables a new differentiable formulation for accelerating algorithms. We further discuss its applications, such as online hyperparameter tuning and learning to optimize. Our proposed methods show superior performance in comprehensive experiments across various problems, which confirms their effectiveness.
May 2, 2025

Differentiable Nonlinear Model Predictive Control

The efficient computation of parametric solution sensitivities is a key challenge in the integration of learning-enhanced methods with nonlinear model predictive control, as their availability is crucial for many learning algorithms. This paper discusses the computation of solution sensitivities of general nonlinear programs using the implicit function theorem and smoothed optimality conditions treated in interior-point methods (IPM). We introduce sequential barrier quadratic programming (SBQP), which generalizes SQP with an IPM quadratic programming (QP) solver by allowing the barrier parameter to approach a prescribed nonnegative target value, recovering classical SQP when this target is zero. Previous works are limited to convex or unconstrained formulations, or lack an implementation for efficient sensitivity evaluation. The publication is accompanied by an efficient open-source implementation within the acados framework, providing both forward and adjoint sensitivities for general optimal control problems, achieving speedups exceeding 3x over the state-of-the-art solvers mpc.pytorch and cvxpygen.