Sequential Monte Carlo (SMC) methods offer a principled approach to Bayesian uncertainty quantification but are traditionally limited by the need for full-batch gradient evaluations. We introduce a scalable variant by incorporating Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) proposals into SMC, enabling efficient mini-batch based sampling. Our resulting SMCSGHMC algorithm outperforms standard stochastic gradient descent (SGD) and deep ensembles across image classification, out-of-distribution (OOD) detection, and transfer learning tasks. We further show that SMCSGHMC mitigates overfitting and improves calibration, providing a flexible, scalable pathway for converting pretrained neural networks into well-calibrated Bayesian models.

We study the Hamiltonian flow for optimization (HF-opt), which simulates the Hamiltonian dynamics for some integration time and resets the velocity to $0$ to decrease the objective function; this is the optimization analogue of the Hamiltonian Monte Carlo algorithm for sampling. For short integration time, HF-opt has the same convergence rates as gradient descent for minimizing strongly and weakly convex functions. We show that by randomizing the integration time in HF-opt, the resulting randomized Hamiltonian flow (RHF) achieves accelerated convergence rates in continuous time, similar to the rates for the accelerated gradient flow. We study a discrete-time implementation of RHF as the randomized Hamiltonian gradient descent (RHGD) algorithm. We prove that RHGD achieves the same accelerated convergence rates as Nesterov's accelerated gradient descent (AGD) for minimizing smooth strongly and weakly convex functions. We provide numerical experiments to demonstrate that RHGD is competitive with classical accelerated methods such as AGD across all settings and outperforms them in certain regimes.

Temporal Graph Networks (TGNs), while being accurate, face significant training inefficiencies due to irregular supervision signals in dynamic graphs, which induce sparse gradient updates. We first theoretically establish that aggregating historical node interactions into pseudo-labels reduces gradient variance, accelerating convergence. Building on this analysis, we propose History-Averaged Labels (HAL), a method that dynamically enriches training batches with pseudo-targets derived from historical label distributions. HAL ensures continuous parameter updates without architectural modifications by converting idle computation into productive learning steps. Experiments on the Temporal Graph Benchmark (TGB) validate our findings and an assumption about slow change of user preferences: HAL accelerates TGNv2 training by up to 15 while maintaining competitive performance. Thus, this work offers an efficient, lightweight, architecture-agnostic, and theoretically motivated solution to label sparsity in temporal graph learning.

End-to-end learning has become a widely applicable and studied problem in training predictive ML models to be aware of their impact on downstream decision-making tasks. These end-to-end models often outperform traditional methods that separate training from the optimization and only myopically focus on prediction error. However, the computational complexity of end-to-end frameworks poses a significant challenge, particularly for large-scale problems. While training an ML model using gradient descent, each time we need to compute a gradient we must solve an expensive optimization problem. We present a meta-optimization method that learns efficient algorithms to approximate optimization problems, dramatically reducing computational overhead of solving the decision problem in general, an aspect we leverage in the training within the end-to-end framework. Our approach introduces a neural network architecture that near-optimally solves optimization problems while ensuring feasibility constraints through alternate projections. We prove exponential convergence, approximation guarantees, and generalization bounds for our learning method. This method offers superior computational efficiency, producing high-quality approximations faster and scaling better with problem size compared to existing techniques. Our approach applies to a wide range of optimization problems including deterministic, single-stage as well as two-stage stochastic optimization problems. We illustrate how our proposed method applies to (1) an electricity generation problem using real data from an electricity routing company coordinating the movement of electricity throughout 13 states, (2) a shortest path problem with a computer vision task of predicting edge costs from terrain maps, (3) a two-stage multi-warehouse cross-fulfillment newsvendor problem, as well as a variety of other newsvendor-like problems.

In quantum thermodynamics, a system is described by a Hamiltonian and a list of non-commuting charges representing conserved quantities like particle number or electric charge, and an important goal is to determine the system's minimum energy in the presence of these conserved charges. In optimization theory, a semi-definite program (SDP) involves a linear objective function optimized over the cone of positive semi-definite operators intersected with an affine space. These problems arise from differing motivations in the physics and optimization communities and are phrased using very different terminology, yet they are essentially identical mathematically. By adopting Jaynes' mindset motivated by quantum thermodynamics, we observe that minimizing free energy in the aforementioned thermodynamics problem, instead of energy, leads to an elegant solution in terms of a dual chemical potential maximization problem that is concave in the chemical potential parameters. As such, one can employ standard (stochastic) gradient ascent methods to find the optimal values of these parameters, and these methods are guaranteed to converge quickly. At low temperature, the minimum free energy provides an excellent approximation for the minimum energy. We then show how this Jaynes-inspired gradient-ascent approach can be used in both first- and second-order classical and hybrid quantum-classical algorithms for minimizing energy, and equivalently, how it can be used for solving SDPs, with guarantees on the runtimes of the algorithms. The approach discussed here is well grounded in quantum thermodynamics and, as such, provides physical motivation underpinning why algorithms published fifty years after Jaynes' seminal work, including the matrix multiplicative weights update method, the matrix exponentiated gradient update method, and their quantum algorithmic generalizations, perform well at solving SDPs.

The present article studies the minimization of convex, L-smooth functions defined on a separable real Hilbert space. We analyze regularized stochastic gradient descent (reg-SGD), a variant of stochastic gradient descent that uses a Tikhonov regularization with time-dependent, vanishing regularization parameter. We prove strong convergence of reg-SGD to the minimum-norm solution of the original problem without additional boundedness assumptions. Moreover, we quantify the rate of convergence and optimize the interplay between step-sizes and regularization decay. Our analysis reveals how vanishing Tikhonov regularization controls the flow of SGD and yields stable learning dynamics, offering new insights into the design of iterative algorithms for convex problems, including those that arise in ill-posed inverse problems. We validate our theoretical findings through numerical experiments on image reconstruction and ODE-based inverse problems.

Averaging, or smoothing, is a fundamental approach to obtain stable, de-noised estimates from noisy observations. In certain scenarios, observations made along trajectories of random dynamical systems are of particular interest. One popular smoothing technique for such a scenario is exponential moving averaging (EMA), which assigns observations a weight that decreases exponentially in their age, thus giving younger observations a larger weight. However, EMA fails to enjoy strong stochastic convergence properties, which stems from the fact that the weight assigned to the youngest observation is constant over time, preventing the noise in the averaged quantity from decreasing to zero. In this work, we consider an adaptation to EMA, which we call $p$-EMA, where the weights assigned to the last observations decrease to zero at a subharmonic rate. We provide stochastic convergence guarantees for this kind of averaging under mild assumptions on the autocorrelations of the underlying random dynamical system. We further discuss the implications of our results for a recently introduced adaptive step size control for Stochastic Gradient Descent (SGD), which uses $p$-EMA for averaging noisy observations.

Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective of simultaneously preventing catastrophic forgetting and allowing forward knowledge transfer during task-incremental learning, while ensuring exact task unlearning and minimizing memory requirements, based on a single neural network model to be adapted. Our proposed solution, privacy-aware lifelong learning (P ALL), involves optimization of task-specific sparse subnetworks with parameter sharing within a single architecture. We additionally utilize an episodic memory rehearsal mechanism to facilitate exact unlearning without performance degradations. We empirically demonstrate the scalability of P ALL across various architectures in image classification, and provide a state-of-the-art solution that uniquely integrates lifelong learning and privacy-aware unlearning mechanisms for responsible AI applications. Lifelong learning algorithms enhance the ability of machine learning models to incrementally acquire new skills or integrate new knowledge over time from sequentially observed data (van de V en et al., 2022). This continual learning capability is essential for models to stay relevant in dynamic environments where the observed data distributions change. A widely studied challenge in this setting is to mitigate catastrophic forgetting, addressing the loss of prior knowledge as new tasks are learned. There has been various strategies proposed to prevent forgetting, while exploiting forward knowledge transfer to efficiently improve performance in new tasks.

One of the defining challenges in federated learning is that of statistical heterogeneity among clients. We address this problem with KARULA, a regularized strategy for personalized federated learning, which constrains the pairwise model dissimilarities between clients based on the difference in their distributions, as measured by a surrogate for the 1-Wasserstein distance adapted for the federated setting. This allows the strategy to adapt to highly complex interrelations between clients, that e.g., clustered approaches fail to capture. We propose an inexact projected stochastic gradient algorithm to solve the constrained problem that the strategy defines, and show theoretically that it converges with smooth, possibly non-convex losses to a neighborhood of a stationary point with rate O(1/K). We demonstrate the effectiveness of KARULA on synthetic and real federated data sets.

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the multi-task distillation could be used to improve such unified modeling. While existing solutions transfer multiple teachers' knowledge in a static way, we propose a self-adaptive distillation method that can dynamically adjust the knowledge amount from each teacher according to the student's current learning ability. Furthermore, as multiple teachers exist, the student's gradient update direction in the distillation is more prone to be erroneous where knowledge forgetting may occur. To avoid this, we propose a knowledge trajectory to record the most essential information that a model has learnt in the past, based on which a trajectory-based distillation loss is designed to guide the student to follow the learning curve similarly in a cost-effective way. We evaluate our method on multiple benchmarking datasets including Cityscapes and NYU-v2. Compared to the state-of-the-art solutions, our method achieves a clearly improvement. The code is provided in the supplementary materials.