Dynamical System Optimization

We develop an optimization framework centered around a core idea: once a (parametric) policy is specified, control authority is transferred to the policy, resulting in an autonomous dynamical system. Thus we should be able to optimize policy parameters without further reference to controls or actions, and without directly using the machinery of approximate Dynamic Programming and Reinforcement Learning. Here we derive simpler algorithms at the autonomous system level, and show that they compute the same quantities as policy gradients and Hessians, natural gradients, proximal methods. Analogs to approximate policy iteration and off-policy learning are also available. Since policy parameters and other system parameters are treated uniformly, the same algorithms apply to behavioral cloning, mechanism design, system identification, learning of state estimators. Tuning of generative AI models is not only possible, but is conceptually closer to the present framework than to Reinforcement Learning.

Spectral Efficiency Maximization for DMA-enabled Multiuser MISO with Statistical CSI

Dynamic metasurface antennas (DMAs) offer the potential to achieve large-scale antenna arrays with low power consumption and reduced hardware costs, making them a promising technology for future communication systems. This paper investigates the spectral efficiency (SE) of DMA-enabled multiuser multiple-input single-output (MISO) systems in both uplink and downlink transmissions, using only statistical channel state information (CSI) to maximize the ergodic sum rate of multiple users. For the uplink system, we consider two decoding rules: minimum mean square error (MMSE) with and without successive interference cancellation (SIC). For both decoders, we derive closed-form surrogates to substitute the original expressions of ergodic sum rate and formulate tractable optimization problems for designing DMA weights. Then, a weighted MMSE (WMMSE)-based algorithm is proposed to maximize the ergodic sum rate. For the downlink system, we derive an approximate expression for the ergodic sum rate and formulate a hybrid analog/digital beamforming optimization problem that jointly optimizes the digital precoder and DMA weights. A penalty dual decomposition (PDD)-based algorithm is proposed by leveraging the fractional programming framework. Numerical results validate the accuracy of the derived surrogates and highlight the superiority of the proposed algorithms over baseline schemes. It is shown that these algorithms are effective across various DMA settings and are particularly well-suited for system design in fast time-varying channels.

Composing Agents to Minimize Worst-case Risk

From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete them. We formalize an agentic workflow as a directed acyclic graph, called an agent graph, where edges represent AI agents and paths correspond to feasible compositions of agents. When deploying these systems in the real world, we need to choose compositions of agents that not only maximize the task success, but also minimize risk where the risk captures requirements like safety, fairness, and privacy. This additionally requires carefully analyzing the low-probability (tail) behaviors of compositions of agents. In this work, we consider worst-case risk minimization over the set of feasible agent compositions. We define worst-case risk as the tail quantile -- also known as value-at-risk -- of the loss distribution of the agent composition where the loss quantifies the risk associated with agent behaviors. We introduce an efficient algorithm that traverses the agent graph and finds a near-optimal composition of agents by approximating the value-at-risk via a union bound and dynamic programming. Furthermore, we prove that the approximation is near-optimal asymptotically for a broad class of practical loss functions. To evaluate our framework, we consider a suite of video game-like control benchmarks that require composing several agents trained with reinforcement learning and demonstrate our algorithm's effectiveness in approximating the value-at-risk and identifying the optimal agent composition.

Dynamic Resource Allocation in Distributed MIMO-LEO Satellite Networks

This paper characterizes the impacts of channel estimation errors and Rician factors on achievable data rate and investigates the user scheduling strategy, combining scheme, power control, and dynamic bandwidth allocation to maximize the sum data rate in the distributed multiple-input-multiple-output (MIMO)-enabled low earth orbit (LEO) satellite networks. However, due to the resource-assignment problem, it is challenging to find the optimal solution for maximizing the sum data rate. To transform this problem into a more tractable form, we first quantify the channel estimation errors based on the minimum mean square error (MMSE) estimator and rigorously derive a closed-form lower bound of the achievable data rate, offering an explicit formulation for resource allocation. Then, to solve the NP-hard problem, we decompose it into three sub-problems, namely, user scheduling strategy, joint combination and power control, and dynamic bandwidth allocation, by using alternative optimization (AO). Specifically, the user scheduling is formulated as a graph coloring problem by iteratively updating an undirected graph based on user requirements, which is then solved using the DSatur algorithm. For the combining weights and power control, the successive convex approximation (SCA) and geometrical programming (GP) are adopted to obtain the sub-optimal solution with lower complexity. Finally, the optimal bandwidth allocation can be achieved by solving the concave problem. Numerical results validate the analytical tightness of the derived bound, especially for large Rician factors, and demonstrate significant performance gains over other benchmarks.

Deep Learning for Continuous-time Stochastic Control with Jumps

In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural networks: one to represent the optimal policy and the other to approximate the value function. Leveraging a continuous-time version of the dynamic programming principle, we derive two different training objectives based on the Hamilton-Jacobi-Bellman equation, ensuring that the networks capture the underlying stochastic dynamics. Empirical evaluations on different problems illustrate the accuracy and scalability of our approach, demonstrating its effectiveness in solving complex, high-dimensional stochastic control tasks.

Reward-Aware Proto-Representations in Reinforcement Learning

In recent years, the successor representation (SR) has attracted increasing attention in reinforcement learning (RL), and it has been used to address some of its key challenges, such as exploration, credit assignment, and generalization. The SR can be seen as representing the underlying credit assignment structure of the environment by implicitly encoding its induced transition dynamics. However, the SR is reward-agnostic. In this paper, we discuss a similar representation that also takes into account the reward dynamics of the problem. We study the default representation (DR), a recently proposed representation with limited theoretical (and empirical) analysis. Here, we lay some of the theoretical foundation underlying the DR in the tabular case by (1) deriving dynamic programming and (2) temporal-difference methods to learn the DR, (3) characterizing the basis for the vector space of the DR, and (4) formally extending the DR to the function approximation case through default features. Empirically, we analyze the benefits of the DR in many of the settings in which the SR has been applied, including (1) reward shaping, (2) option discovery, (3) exploration, and (4) transfer learning. Our results show that, compared to the SR, the DR gives rise to qualitatively different, reward-aware behaviour and quantitatively better performance in several settings.

Finding Maximum Independent Sets in Dynamic Graphs using Unsupervised Learning

We present the first unsupervised learning model for finding Maximum Independent Sets (MaxIS) in dynamic graphs where edges change over time. Our method combines structural learning from graph neural networks (GNNs) with a learned distributed update mechanism that, given an edge addition or deletion event, modifies nodes' internal memories and infers their MaxIS membership in a single, parallel step. We parameterize our model by the update mechanism's radius and investigate the resulting performance-runtime tradeoffs for various dynamic graph topologies. We evaluate our model against state-of-the-art MaxIS methods for static graphs, including a mixed integer programming solver, deterministic rule-based algorithms, and a heuristic learning framework based on dynamic programming and GNNs. Across synthetic and real-world dynamic graphs of 100-10,000 nodes, our model achieves competitive approximation ratios with excellent scalability; on large graphs, it significantly outperforms the state-of-the-art heuristic learning framework in solution quality, runtime, and memory usage. Our model generalizes well on graphs 100x larger than the ones used for training, achieving performance at par with both a greedy technique and a commercial mixed integer programming solver while running 1.5-23x faster than greedy.

Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms

Dynamic programming (DP) algorithms for combinatorial optimization problems work with taking maximization, minimization, and classical addition in their recursion algorithms. The associated value functions correspond to convex polyhedra in the max plus semiring. Existing Neural Algorithmic Reasoning models, however, rely on softmax-normalized dot-product attention where the smooth exponential weighting blurs these sharp polyhedral structures and collapses when evaluated on out-of-distribution (OOD) settings. We introduce Tropical attention, a novel attention function that operates natively in the max-plus semiring of tropical geometry. We prove that Tropical attention can approximate tropical circuits of DP-type combinatorial algorithms. We then propose that using Tropical transformers enhances empirical OOD performance in both length generalization and value generalization, on algorithmic reasoning tasks, surpassing softmax baselines while remaining stable under adversarial attacks. We also present adversarial-attack generalization as a third axis for Neural Algorithmic Reasoning benchmarking. Our results demonstrate that Tropical attention restores the sharp, scale-invariant reasoning absent from softmax.

Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging

Diffusion trajectory distillation methods aim to accelerate sampling in diffusion models, which produce high-quality outputs but suffer from slow sampling speeds. These methods train a student model to approximate the multi-step denoising process of a pretrained teacher model in a single step, enabling one-shot generation. However, theoretical insights into the trade-off between different distillation strategies and generative quality remain limited, complicating their optimization and selection. In this work, we take a first step toward addressing this gap. Specifically, we reinterpret trajectory distillation as an operator merging problem in the linear regime, where each step of the teacher model is represented as a linear operator acting on noisy data. These operators admit a clear geometric interpretation as projections and rescalings corresponding to the noise schedule. During merging, signal shrinkage occurs as a convex combination of operators, arising from both discretization and limited optimization time of the student model. We propose a dynamic programming algorithm to compute the optimal merging strategy that maximally preserves signal fidelity. Additionally, we demonstrate the existence of a sharp phase transition in the optimal strategy, governed by data covariance structures. Our findings enhance the theoretical understanding of diffusion trajectory distillation and offer practical insights for improving distillation strategies.

Spline Dimensional Decomposition with Interpolation-based Optimal Knot Selection for Stochastic Dynamic Analysis

Forward uncertainty quantification in dynamic systems is challenging due to non-smooth or locally oscillating nonlinear behaviors. Spline dimensional decomposition (SDD) effectively addresses such nonlinearity by partitioning input coordinates via knot placement, yet its accuracy is highly sensitive to the location of internal knots. Optimizing knots through sequential quadratic programming can be effective, yet the optimization process becomes computationally intense. We propose a computationally efficient, interpolation-based method for optimal knot selection in SDD. The method involves three steps: (1) interpolating input-output profiles, (2) defining subinterval-based reference regions, and (3) selecting optimal knot locations at maximum gradient points within each region. The resulting knot vector is then applied to SDD for accurate approximation of non-smooth and locally oscillating responses. A modal analysis of a lower control arm demonstrates that SDD with the proposed knot selection achieves higher accuracy than SDD with uniformly or randomly spaced knots, and also a Gaussian process surrogate model. The proposed SDD exhibits the lowest relative variance error (2.89%), compared to SDD with uniformly spaced knots (12.310%), randomly spaced knots (15.274%), and Gaussian process (5.319%) in the first natural frequency distribution. All surrogate models are constructed using the same 401 simulation datasets, and the relative errors are evaluated against a 2000-sample Monte Carlo simulation. The scalability and applicability of proposed method are demonstrated through stochastic and reliability analyses of mathematical functions (N=1, 3) and a lower control arm system (N=10). The results confirm that both second-moment statistics and reliability estimates can be accurately achieved with only a few hundred function evaluations or finite element simulations.