arXiv subjects

Harsha Honnappa

Publications and source records attributed to Harsha Honnappa.

At least 19 recordsLinked to original sources

arXiv2026

The BAR-SOT Method: Long-term Average Cost Control as Stochastic Optimal Self-Transport

We reformulate average-cost (ergodic) control of a Markov jump process as a finite-horizon stochastic optimal transport (SOT) problem that jointly optimizes over the controlled evolution and the marginal law from which it starts and returns to (i.e., a self-transport). The constraint relating the marginal flow to the controlled generator is the basic adjoint relationship (BAR), so we call the resulting problem BAR-SOT. For any time horizon T>0, its optimal value is a constant scaling of the long-run average-cost rate. We give three equivalent formulations (through controlled processes, a Fokker--Planck constraint, and relaxed marginal measures) and show that the optimal dual is a stationary potential plus a term linear in time, with slope equal to the rate. A relative-entropy penalty on the control yields a cost-tilted Schrodinger bridge problem, computable by a Sinkhorn-type iteration when every transition rate is controlled, whose value converges to the unregularized optimum as the penalty vanishes. We develop the theory for finite Markov decision processes and then for general controlled Markov jump processes. A neural parametrization of the dual, trained as a physics-informed neural network (PINN), that encodes Harrison's equivalent-workload formulation (see Harrison 2000) matches the strong reinforcement-learning baseline of Dai and Gluzman (2022); numerically conditioning the fit of a sub-dominant transverse correction then improves on both that baseline and the best priority heuristic. On the input-queued switch, a graph-attention parametrization of the dual improves on the strongest matching heuristic we are aware of, with a parameter count that does not grow with the switch size.

math.OC↗

arXiv2026

Narrow-Shell Stochasticity in Source-Sink Models of the Low Earth Orbit Environment

Deterministic source-sink models are widely used to assess the long-term evolution, capacity, and sustainability of the low Earth orbit (LEO) environment. These models propagate shell-averaged populations through ordinary differential equations (ODEs), relying on individual collision, disposal, and decay events to average out within sufficiently large altitude shells. As constellation traffic is increasingly organized into kilometer- and sub-kilometer-scale shells, this averaging assumption becomes strained. We formulate the multi-shell, multi-species LEO environment as a Markov jump process and, from this formulation, recover the conventional source-sink ODE as a large-volume limit and derive a stochastic differential equation (SDE) approximation whose fluctuations scale as V^{-1/2} in the per-shell volume V. The diffusion approximation is validated against an exact discrete-event simulation of the underlying jump process. Sweeping V at fixed spatial density over the 450-800 km band, we find that the two descriptions agree at shell volumes comparable to those used in established source-sink models but diverge as shells narrow. At the finest shell volume considered, the mean debris population reaches roughly 4.5 times the ODE prediction, with several realizations undergoing runaway growth absent from the ODE trajectory. This departure is driven by nonlinear collision terms, through which population variance and covariance raise expected collision rates, generating further debris and reinforcing the collision-debris feedback. Narrow-shell stochasticity thus both widens the outcome distribution and shifts the expected trajectory. Because the stochastic model shares its parameterization with the deterministic one, it provides a scale-consistent extension of existing source-sink models for evaluating shell configuration, collision risk, and long-term LEO sustainability.

astro-ph.EP↗

arXiv2026

Stochastic Dynamics of Low Earth Orbit Near Full Capacity

The capacity of Low Earth Orbit (LEO) to sustain space operations is under mounting pressure from megaconstellations, legacy fragmentation debris, and new payload classes. Existing assessments of orbital capacity and debris evolution are largely deterministic, tracking mean populations of intact satellites and fragments with ordinary differential equations; they cannot capture the inherent randomness of collisions, breakup sizes, and launch schedules. We develop a stochastic extension of the two-species Lotka--Volterra model of Bradley and Wein, formulated as a density-dependent Markov chain, and study its deterministic and stochastic scaling limits. Because intacts and fragments differ by many orders of magnitude, these limits emerge on distinct time-scales, and different pathways to a collisional Kessler cascade become visible only on the appropriate time horizon. On a fast intact time-scale we obtain an ODE approximation and a Gaussian SDE approximation; on an intermediate fragment time-scale we obtain an ODE approximation, a Gaussian SDE approximation, and the critical Kessler threshold, above which the ODE approximation runs away in Kessler syndrome. Crucially, on a third, slow time-scale at the critical threshold, the fragment count converges to a Feller diffusion, in which runaway is triggered purely by fluctuations rather than by the drift---an effect the ODE approximations and their Gaussian SDE approximations cannot see. Debris runaway may occur sooner, and with higher probability, than deterministic models predict: the intact population can appear well-behaved while fragments quietly accumulate risk. Constellation deployment, debris-removal investment, and slot allocation should account for these stochastic effects, and planning for runaway must depend on the variance of the collision dynamics, not on the mean alone.

math.PR↗

arXiv2026

Robust Filtering of Lévy-driven Stochastic Models

We study robust nonlinear filtering for stochastic models driven by Lévy processes, where the signal and observation processes are coupled through common Brownian and jump noise. Robustness, defined as the continuous dependence of the filter on the observation path, is essential whenever the observation process deviates from the idealized model, for instance when a path must be reconstructed from discrete-time samples. This question is well understood for continuous semimartingale systems but largely open in the presence of jumps. We construct a version of the filter and establish its continuity in two regimes. For processes with finitely many jumps on compact intervals, we prove continuity in both the rough $p$-variation and $p$-variation topologies on cadlag path space, without requiring a separability condition on the jump coefficients. For processes with infinitely many jumps, we prove continuity in a modified rough $p$-variation topology adapted to cadlag geometric rough paths, under an additional separability assumption. In both cases, our approach relies on Stratonovich and Marcus flow decompositions rather than the Itô-based methods of recent work. The resulting geometric rough-path lifts yield pathwise convergence guarantees and can be constructed directly from discrete observations without knowledge of the underlying probability law.

math.PR↗

arXiv2026

The Variational Approach in Filtering and Correlated Noise

The variational formulation of nonlinear filtering due to Mitter and Newton characterizes the filtering distribution as the unique minimizer of a free energy functional involving the relative entropy with respect to the prior and an expected energy. This formulation rests on an absolute continuity condition between the joint path measure and a product reference measure. We prove that this condition necessarily fails whenever the signal and observation diffusions share a common noise source. Specifically we show that the joint and product measures are mutually singular, so no choice of reference measure can salvage the formulation. We then introduce a conditional variational principle that replaces the prior with a reference measure that preserves the noise correlation structure. This generalization recovers the Mitter--Newton formulation as a special case when the noises are independent, and yields an explicit free energy characterization of the filter in the linear correlated-noise setting.

math.PR↗

arXiv2026

Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity

In this work, we study a natural nonparametric estimator of the transition probability matrices of a finite controlled Markov chain. We consider an offline setting with a fixed dataset, collected using a so-called logging policy. We develop sample complexity bounds for the estimator and establish conditions for minimaxity. Our statistical bounds depend on the logging policy through its mixing properties. We show that achieving a particular statistical risk bound involves a subtle and interesting trade-off between the strength of the mixing properties and the number of samples. We demonstrate the validity of our results under various examples, such as ergodic Markov chains, weakly ergodic inhomogeneous Markov chains, and controlled Markov chains with non-stationary Markov, episodic, and greedy controls. Lastly, we use these sample complexity bounds to establish concomitant ones for offline evaluation of stationary Markov control policies.

stat.ML↗

arXiv2026

A stochastic optimization algorithm for revenue maximization in a service system with balking customers

This paper analyzes a service system modeled as a single-server queue, in which the service provider aims to dynamically maximize the expected revenue per unit of time. This is achieved by constructing a stochastic gradient descent algorithm that dynamically adjusts the price. A key feature of our modeling framework is that customers may choose to balk - that is, decide not to join - when facing high congestion. A notable strength of our approach is that the revenue-maximizing algorithm relies solely on information about effective arrivals, meaning that only the behavior of customers who choose not to balk is observable and used in decision-making. This results in an elaborate interplay between the pricing policy and the effective arrival process, yielding a non-standard state dependent queueing process. An important contribution of our work concerns a novel Infinitesimal Perturbation Analysis (IPA) procedure that is able to consistently estimate the stationary effective arrival rate. This is further leveraged to construct an iterative algorithm that converges, under mild regularity conditions, to the optimal price with provable asymptotic guarantees.

math.OC↗

arXiv2026

Neural Diffusion Intensity Models for Point Process Data

Cox processes model overdispersed point process data via a latent stochastic intensity, but both nonparametric estimation of the intensity model and posterior inference over intensity paths are typically intractable, relying on expensive MCMC methods. We introduce Neural Diffusion Intensity Models, a variational framework for Cox processes driven by neural SDEs. Our key theoretical result, based on enlargement of filtrations, shows that conditioning on point process observations preserves the diffusion structure of the latent intensity with an explicit drift correction. This guarantees the variational family contains the true posterior, so that ELBO maximization coincides with maximum likelihood estimation under sufficient model capacity. We design an amortized encoder architecture that maps variable-length event sequences to posterior intensity paths by simulating the drift-corrected SDE, replacing repeated MCMC runs with a single forward pass. Experiments on synthetic and real-world data demonstrate accurate recovery of latent intensity dynamics and posterior paths, with orders-of-magnitude speedups over MCMC-based methods.

cs.LG↗

arXiv2026

Linear Quadratic Control with Non-Markovian and Non-Semimartingale Noise Models

The standard linear quadratic Gaussian (LQG) framework assumes a Brownian noise process and relies on classical stochastic calculus tools, such as those based on Itô calculus. In this paper, we solve a generalized linear quadratic optimal control problem where the process and measurement noises can be non-Markovian and non-semimartingale stochastic processes with sample paths that have low Hölder regularity. Since these noise models do not, in general, permit the use of the standard Itô calculus, we employ rough path theory to formulate and solve the problem. By leveraging signature representations and controlled rough paths, we derive the optimal state estimation and control strategies.

eess.SY↗

arXiv2026

The Pontryagin maximum principle and $Q$-functions in rough environments

We derive the Pontryagin maximum principle and $Q$-functions for the relaxed control of noisy rough differential equations. Our main tool is the development of a novel differentiation procedure along `spike variation' perturbations of the optimal state-control pair. We then exploit our development of the infinitesimal $Q$-function (also known as the $q$-function) to derive a policy improvement algorithm for settings with entropic cost constraints.

math.OC↗

arXiv2025

Drift Optimization of Regulated Stochastic Models Using Sample Average Approximation

This paper introduces a drift optimization model of stochastic optimization problems driven by regulated stochastic processes. A broad range of problems across operations research, machine learning, and statistics can be viewed as optimizing the "drift" associated with a process by minimizing a cost functional, while respecting path constraints imposed by a Lipschitz continuous regulator. Towards an implementable solution to such infinite-dimensional problems, we develop the fundamentals of a Sample Average Approximation (SAA) method that incorporates (i) path discretization, (ii) function-space discretization, and (iii) Monte Carlo sampling, and that is solved using an optimization recursion such as mirror descent. We start by constructing pathwise directional derivatives for use within the SAA method, followed by consistency and complexity calculations. The characterized complexity is expressed as a function of the number of optimization steps, and the computational effort involved in (i)--(iii), leading to guidance on how to trade-off the computational effort allocated to optimization steps versus the "dimension reduction" steps in (i)--(iii).

math.OC↗

arXiv2025

Adaptive Estimation of the Transition Density of Controlled Markov Chains

Estimating the transition dynamics of controlled Markov chains is crucial in fields such as time series analysis, reinforcement learning, and system exploration. Traditional non-parametric density estimation methods often assume independent samples and require oracle knowledge of smoothness parameters like the Hölder continuity coefficient. These assumptions are unrealistic in controlled Markovian settings, especially when the controls are non-Markovian, since such parameters need to hold uniformly over all control values. To address this gap, we propose an adaptive estimator for the transition densities of controlled Markov chains that does not rely on prior knowledge of smoothness parameters or assumptions about the control sequence distribution. Our method builds upon recent advances in adaptive density estimation by selecting an estimator that minimizes a loss function {and} fitting the observed data well, using a constrained minimax criterion over a dense class of estimators. We validate the performance of our estimator through oracle risk bounds, employing both randomized and deterministic versions of the Hellinger distance as loss functions. This approach provides a robust and flexible framework for estimating transition densities in controlled Markovian systems without imposing strong assumptions.

math.ST↗

arXiv2024

Renewal Processes Represented as Doubly Stochastic Poisson Processes

This paper gives an elementary proof for the following theorem: a renewal process can be represented by a doubly-stochastic Poisson process (DSPP) if and only if the Laplace-Stieltjes transform of the inter-arrival times is of the following form: $$ϕ(θ)=λ\left[λ+θ+k\int_0^\infty\left(1-e^{-θz}\right)\,dG(z)\right]^{-1},$$ for some positive real numbers $λ, k$, and some distribution function $G$ with $G(\infty)=1$. The intensity process $Λ(t)$ of the corresponding DSPP jumps between $λ$ and $0$, with the time spent at $λ$ being independent random variables that are exponentially distributed with mean $1/k$, and the time spent at $0$ being independent random variables with distribution function $G$.

math.PR↗

arXiv2024

The Small-Noise Limit of the Most Likely Element is the Most Likely Element in the Small-Noise Limit

In this paper, we study the Onsager-Machlup function and its relationship to the Freidlin-Wentzell function for measures equivalent to arbitrary infinite dimensional Gaussian measures. The Onsager-Machlup function can serve as a density on infinite dimensional spaces, where a uniform measure does not exist, and has been seen as the Lagrangian for the ``most likely element". The Freidlin-Wentzell rate function is the large deviations rate function for small-noise limits and has also been identified as a Lagrangian for the ``most likely element". This leads to a conundrum - what is the relationship between these two functions? We show both pointwise and $Γ$-convergence (which is essentially the convergence of minimizers) of the Onsager-Machlup function under the small-noise limit to the Freidlin-Wentzell function - and give an expression for both. That is, we show that the small-noise limit of the most likely element is the most likely element in the small noise limit for infinite dimensional measures that are equivalent to a Gaussian. Examples of measures include the law of solutions to path-dependent stochastic differential equations and the law of an infinite system of random algebraic equations.

math.PR↗

arXiv2024

Pathwise Relaxed Optimal Control of Rough Differential Equations

This note lays part of the theoretical ground for a definition of differential systems modeling reinforcement learning in continuous time non-Markovian rough environments. Specifically we focus on optimal relaxed control of rough equations (the term relaxed referring to the fact that controls have to be considered as measure valued objects). With reinforcement learning in view, our reward functions encompass forms that involve an entropy-type term favoring exploration. In this context, our contribution focuses on a careful definition of the corresponding relaxed Hamilton-Jacobi-Bellman (HJB)-type equation. A substantial part of our endeavor consists in a precise definition of the notion of test function and viscosity solution for the rough relaxed PDE obtained in this framework. Note that this task is often merely sketched in the rough viscosity literature, in spite of the fact that it gives a proper meaning to the differential system at stake. In the last part of the paper we prove that the natural value function in our context solves a relaxed rough HJB equation in the viscosity sense.

math.OC↗

arXiv2023

Distributed Sparse Regression via Penalization

We study sparse linear regression over a network of agents, modeled as an undirected graph (with no centralized node). The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint -- the latter being instrumental to obtain distributed solution methods. While penalty-based consensus methods have been extensively studied in the optimization literature, their statistical and computational guarantees in the high dimensional setting remain unclear. This work provides an answer to this open problem. Our contribution is two-fold. First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates. Second, we show that the proximal-gradient algorithm applied to the penalized problem, which naturally leads to distributed implementations, converges linearly up to a tolerance of the order of the centralized statistical error -- the rate scales as $\mathcal{O}(d)$, revealing an unavoidable speed-accuracy dilemma.Numerical results demonstrate the tightness of the derived sample rate and convergence rate scalings.

cs.LG↗

arXiv2022

Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency

This paper considers data-driven chance-constrained stochastic optimization problems in a Bayesian framework. Bayesian posteriors afford a principled mechanism to incorporate data and prior knowledge into stochastic optimization problems. However, the computation of Bayesian posteriors is typically an intractable problem, and has spawned a large literature on approximate Bayesian computation. Here, in the context of chance-constrained optimization, we focus on the question of statistical consistency (in an appropriate sense) of the optimal value, computed using an approximate posterior distribution. To this end, we rigorously prove a frequentist consistency result demonstrating the convergence of the optimal value to the optimal value of a fixed, parameterized constrained optimization problem. We augment this by also establishing a probabilistic rate of convergence of the optimal value. We also prove the convex feasibility of the approximate Bayesian stochastic optimization problem. Finally, we demonstrate the utility of our approach on an optimal staffing problem for an M/M/c queueing model.

math.ST↗

arXiv2021

On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making

We study data-driven decision-making problems in the Bayesian framework, where the expectation in the Bayes risk is replaced by a risk-sensitive entropic risk measure. We focus on problems where calculating the posterior distribution is intractable, a typical situation in modern applications with large datasets and complex data generating models. We leverage a dual representation of the entropic risk measure to introduce a novel risk-sensitive variational Bayesian (RSVB) framework for jointly computing a risk-sensitive posterior approximation and the corresponding decision rule. The proposed RSVB framework can be used to extract computational methods for doing risk-sensitive approximate Bayesian inference. We show that our general framework includes two well-known computational methods for doing approximate Bayesian inference viz. naive VB and loss-calibrated VB. We also study the impact of these computational approximations on the predictive performance of the inferred decision rules and values. We compute the convergence rates of the RSVB approximate posterior and also of the corresponding optimal value and decision rules. We illustrate our theoretical findings in both parametric and nonparametric settings with the help of three examples: the single and multi-product newsvendor model and Gaussian process classification.

math.OC↗