arXiv subjects

Kushagra Gupta

Publications and source records attributed to Kushagra Gupta.

14 recordsLinked to original sources

arXiv2026

A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions

While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this end, we propose Function Projection for Flow Matching (FP-FM), an algorithm that directly conditions generation on samples from the target distribution. FP-FM learns basis functions to span the velocity fields corresponding to a set of training distributions, and adapts to new distributions by computing a simple least-squares projection onto this basis. This enables efficient generation of samples from diverse target distributions without additional training at inference time. We further introduce multiple variants of FP-FM that provide a trade-off in expressivity and compute by enriching the coefficient calculation, e.g., by making the coefficients dependent on time. FP-FM achieves greatly improved precision and recall relative to baselines across synthetic and image-based datasets, with especially strong gains on unseen distributions.

cs.LG↗

arXiv2026

Interleaved Information Structures in Dynamic Games: A General Framework with Application to the Linear-Quadratic Case

A fundamental problem in noncooperative dynamic game theory is the computation of Nash equilibria under different information structures, which specify the information available to each agent during decision-making. Prior work has extensively studied equilibrium solutions for two canonical information structures: feedback, where agents observe the current state at each time, and open-loop, where agents only observe the initial state. However, these paradigms are often too restrictive to capture realistic settings exhibiting interleaved information structures, in which each agent observes only a subset of other agents at every timestep. To date, there is no systematic framework for modeling and solving dynamic games under arbitrary interleaved information structures. To this end, we make two main contributions. First, we introduce a method to model deterministic dynamic games with arbitrary interleaved information structures as Mathematical Program Networks (MPNs), where the network structure encodes the informational dependencies between agents. Second, for linear-quadratic (LQ) dynamic games, we leverage the MPN formulation to develop a systematic procedure for deriving Riccati-like equations that characterize Nash equilibria. Finally, we illustrate our approach through an example involving three agents exhibiting a cyclic information structure.

cs.GT↗

arXiv2025

UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles

Safe large-scale coordination of multiple cooperative connected autonomous vehicles (CAVs) hinges on communication that is both efficient and interpretable. Existing approaches either rely on transmitting high-bandwidth raw sensor data streams or neglect perception and planning uncertainties inherent in shared data, resulting in systems that are neither scalable nor safe. To address these limitations, we propose Uncertainty-Guided Natural Language Cooperative Autonomous Planning (UNCAP), a vision-language model-based planning approach that enables CAVs to communicate via lightweight natural language messages while explicitly accounting for perception uncertainty in decision-making. UNCAP features a two-stage communication protocol: (i) an ego CAV first identifies the subset of vehicles most relevant for information exchange, and (ii) the selected CAVs then transmit messages that quantitatively express their perception uncertainty. By selectively fusing messages that maximize mutual information, this strategy allows the ego vehicle to integrate only the most relevant signals into its decision-making, improving both the scalability and reliability of cooperative planning. Experiments across diverse driving scenarios show a 63% reduction in communication bandwidth with a 31% increase in driving safety score, a 61% reduction in decision uncertainty, and a four-fold increase in collision distance margin during near-miss events. Project website: https://uncap-project.github.io/

cs.RO↗

arXiv2025

Monotonic Transformation Invariant Multi-task Learning

Multi-task learning (MTL) algorithms typically rely on schemes that combine different task losses or their gradients through weighted averaging. These methods aim to find Pareto stationary points by using heuristics that require access to task loss values, gradients, or both. In doing so, a central challenge arises because task losses can be arbitrarily scaled relative to one another, causing certain tasks to dominate training and degrade overall performance. A recent advance in cooperative bargaining theory, the Direction-based Bargaining Solution (DiBS), yields Pareto stationary solutions immune to task domination because of its invariance to monotonic nonaffine task loss transformations. However, the convergence behavior of DiBS in nonconvex MTL settings is currently not understood. To this end, we prove that under standard assumptions, a subsequence of DiBS iterates converges to a Pareto stationary point when task losses are nonconvex, and propose DiBS-MTL, an adaptation of DiBS to the MTL setting which is more computationally efficient that prior bargaining-inspired MTL approaches. Finally, we empirically show that DiBS-MTL is competitive with leading MTL methods on standard benchmarks, and it drastically outperforms state-of-the-art baselines in multiple examples with poorly-scaled task losses, highlighting the importance of invariance to nonaffine monotonic transformations of the loss landscape. Code available at https://github.com/suryakmurthy/dibs-mtl

cs.LG↗

arXiv2025

Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles

Cooperative bargaining games are widely used to model resource allocation and conflict resolution. Traditional solutions assume the mediator can access agents utility function values and gradients. However, there is an increasing number of settings, such as human AI interactions, where utility values may be inaccessible or incomparable due to unknown, nonaffine transformations. To model such settings, we consider that the mediator has access only to agents most preferred directions, i.e., normalized utility gradients in the decision space. To this end, we propose a cooperative bargaining algorithm where a mediator has access to only the direction oracle of each agent. We prove that unlike popular approaches such as the Nash and Kalai Smorodinsky bargaining solutions, our approach is invariant to monotonic nonaffine transformations, and that under strong convexity and smoothness assumptions, this approach enjoys global asymptotic convergence to Pareto stationary solutions. Moreover, we show that the bargaining solutions found by our algorithm also satisfy the axioms of symmetry and (under slightly stronger conditions) independence of irrelevant alternatives, which are popular in the literature. Finally, we conduct experiments in two domains, multi agent formation assignment and mediated stock portfolio allocation, which validate these theoretic results. All code for our experiments can be found at https://github.com/suryakmurthy/dibs_bargaining.

cs.GT↗

arXiv2025

Real-Time Privacy Preservation for Robot Visual Perception

Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.

cs.CV↗

arXiv2025

More Information is Not Always Better: Connections between Zero-Sum Local Nash Equilibria in Feedback and Open-Loop Information Patterns

Non-cooperative dynamic game theory provides a principled approach to modeling sequential decision-making among multiple noncommunicative agents. A key focus has been on finding Nash equilibria in two-agent zero-sum dynamic games under various information structures. A well-known result states that in linear-quadratic games, unique Nash equilibria under feedback and open-loop information structures yield identical trajectories. Motivated by two key perspectives -- (i) many real-world problems extend beyond linear-quadratic settings and lack unique equilibria, making only local Nash equilibria computable, and (ii) local open-loop Nash equilibria (OLNE) are easier to compute than local feedback Nash equilibria (FBNE) -- it is natural to ask whether a similar result holds for local equilibria in zero-sum games. To this end, we establish that for a broad class of zero-sum games with potentially nonconvex-nonconcave objectives and nonlinear dynamics: (i) the state/control trajectory of a local FBNE satisfies local OLNE first-order optimality conditions, and vice versa, (ii) a local FBNE trajectory satisfies local OLNE second-order necessary conditions, (iii) a local FBNE trajectory satisfying feedback sufficiency conditions also constitutes a local OLNE, and (iv) with additional hard constraints on agents' actuations, a local FBNE where strict complementarity holds also satisfies local OLNE first-order optimality conditions, and vice versa.

cs.GT↗

arXiv2025

A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation

Many reinforcement learning (RL) algorithms are impractical for training in operational systems or computationally expensive high-fidelity simulations, as they require large amounts of data. Meanwhile, low-fidelity simulators, e.g., reduced-order models, heuristic rewards, or learned world models, can cheaply provide useful data, even if they are too coarse for zero-shot transfer. We propose multi-fidelity policy gradients (MFPGs), a sample-efficient RL framework that mixes scarce target-environment data with a control variate formed from abundant low-fidelity simulation data to construct an unbiased, variance-reduced estimator for on-policy policy gradients. We instantiate the framework with a practical, multi-fidelity variant of the classical REINFORCE algorithm. Under standard assumptions, the MFPG estimator guarantees asymptotic convergence to locally optimal policies in the target environment and achieves faster finite-sample convergence than standard REINFORCE. We evaluate MFPG on robotics benchmark tasks with limited high-fidelity data but abundant off-dynamics, low-fidelity data. When low-fidelity data are neutral or beneficial and dynamics gaps are mild-moderate, MFPG is, among the evaluated off-dynamics RL and low-fidelity-only approaches, the only method that consistently achieves statistically significant improvements over a high-fidelity-only baseline. When low-fidelity data become harmful, MFPG exhibits the strongest robustness, whereas strong off-dynamics RL methods exploit low-fidelity data aggressively and fail much more severely. An additional experiment with anti-correlated high- and low-fidelity rewards shows MFPG can remain effective even under reward misspecification. MFPG thus offers a reliable paradigm for exploiting cheap low-fidelity data (e.g., for efficient sim-to-real transfer) while managing the trade-off between policy performance and data collection cost.

cs.LG↗

arXiv2024

Inferring Foresightedness in Dynamic Noncooperative Games

Dynamic game theory is an increasingly popular tool for modeling multi-agent, e.g. human-robot, interactions. Game-theoretic models presume that each agent wishes to minimize a private cost function that depends on others' actions. These games typically evolve over a fixed time horizon, specifying how far into the future each agent plans. In practical settings, however, decision-makers may vary in foresightedness, or how much they care about their current cost in relation to their past and future costs. We conjecture that quantifying and estimating each agent's foresightedness from online data will enable safer and more efficient interactions with other agents. To this end, we frame this inference problem as an inverse dynamic game. We consider a specific objective function parametrization that smoothly interpolates myopic and farsighted planning. Games of this form are readily transformed into parametric mixed complementarity problems; we exploit the directional differentiability of solutions to these problems with respect to their hidden parameters to solve for agents' foresightedness. We conduct three experiments: one with synthetically generated delivery robot motion, one with real-world data involving people walking, biking, and driving vehicles, and one using high-fidelity simulators. The results of these experiments demonstrate that explicitly inferring agents' foresightedness enables game-theoretic models to make 33% more accurate models for agents' behavior.

cs.RO↗

arXiv2024

Second-Order Algorithms for Finding Local Nash Equilibria in Zero-Sum Games

Zero-sum games arise in a wide variety of problems, including robust optimization and adversarial learning. However, algorithms deployed for finding a local Nash equilibrium in these games often converge to non-Nash stationary points. This highlights a key challenge: for any algorithm, the stability properties of its underlying dynamical system can cause non-Nash points to be potential attractors. To overcome this challenge, algorithms must account for subtleties involving the curvatures of players' costs. To this end, we leverage dynamical system theory and develop a second-order algorithm for finding a local Nash equilibrium in the smooth, possibly nonconvex-nonconcave, zero-sum game setting. First, we prove that this novel method guarantees convergence to only local Nash equilibria with an asymptotic local \textit{linear} convergence rate. We then interpret a version of this method as a modified Gauss-Newton algorithm with local \textit{superlinear} convergence to the neighborhood of a point that satisfies first-order local Nash equilibrium conditions. In comparison, current related state-of-the-art methods with similar guarantees do not offer convergence rates in the nonconvex-nonconcave setting. Furthermore, we show that this approach naturally generalizes to settings with convex and potentially coupled constraints while retaining earlier guarantees of convergence to only local (generalized) Nash equilibria. Code for our experiments can be found at https://github.com/CLeARoboticsLab/ZeroSumGameSolve.jl.

cs.GT↗

arXiv2023

Game-theoretic Occlusion-Aware Motion Planning: an Efficient Hybrid-Information Approach

We present a novel algorithm for game-theoretic trajectory planning, tailored for settings in which agents can only observe one another in specific regions of the state space. Such problems arise naturally in the context of multi-robot navigation, where occlusions due to environment geometry naturally mask agents' view of one another. In this paper, we formalize these settings as dynamic games with a hybrid information structure, which interleaves so-called "open-loop" periods (in which agents cannot observe one another) with "feedback" periods (with full state observability). We present two main contributions. First, we study a canonical variant of these hybrid information games in which agents' dynamics are linear, and objectives are convex and quadratic. Here, we build upon classical solution methods for the open-loop and feedback variants of these games to derive an algorithm for the hybrid information case that matches the cubic runtime of the classical settings. Second, we consider a far broader class of problems in which agents' dynamics are nonlinear, and objectives are nonquadratic; we reduce these problems to sequences of hybrid information linear-quadratic games and empirically demonstrate that iteratively solving these simpler problems with the proposed algorithm yields reliable convergence to approximate Nash equilibria through simulation studies of overtaking and intersection traffic scenarios.

cs.MA↗

arXiv2021

Bayesian equation selection on sparse data for discovery of stochastic dynamical systems

Often the underlying system of differential equations driving a stochastic dynamical system is assumed to be known, with inference conditioned on this assumption. We present a Bayesian framework for discovering this system of differential equations under assumptions that align with real-life scenarios, including the availability of relatively sparse data. Further, we discuss computational strategies that are critical in teasing out the important details about the dynamical system and algorithmic innovations to solve for acute parameter interdependence in the absence of rich data. This gives a complete Bayesian pathway for model identification via a variable selection paradigm and parameter estimation of the corresponding model using only the observed data. We present detailed computations and analysis of the Lorenz-96, Lorenz-63, and the Orstein-Uhlenbeck system using the Bayesian framework we propose.

stat.ME↗

arXiv2020

Estimating Monte Carlo variance from multiple Markov chains

Modern computational advances have enabled easy parallel implementations of Markov chain Monte Carlo (MCMC). However, almost all work in estimating the variance of Monte Carlo averages, including the efficient batch means (BM) estimator, focuses on a single-chain MCMC run. We demonstrate that simply averaging covariance matrix estimators from multiple chains can yield critical underestimates in small Monte Carlo sample sizes, especially for slow-mixing Markov chains. We extend the work of \cite{arg:and:2006} and propose a multivariate replicated batch means (RBM) estimator that utilizes information from parallel chains, thereby correcting for the underestimation. Under weak conditions on the mixing rate of the process, RBM is strongly consistent and exhibits similar large-sample bias and variance to the BM estimator. We also exhibit superior theoretical properties of RBM by showing that the (negative) bias in the RBM estimator is less than the average BM estimator in the presence of positive correlation in MCMC. Consequently, in small runs, the RBM estimator can be dramatically superior and this is demonstrated through a variety of examples.

stat.ME↗

arXiv2013

Detection and prevention of botnets and malware in an enterprise network

One of the most significant threats faced by enterprise networks today is from Bots. A Bot is a program that operates as an agent for a user and runs automated tasks over the internet, at a much higher rate than would be possible for a human alone. A collection of Bots in a network, used for malicious purposes is referred to as a Botnet. Bot attacks can range from localized attacks like key-logging to network intensive attacks like Distributed Denial of Service (DDoS). In this paper, we suggest a novel approach that can detect and combat Bots. The proposed solution adopts a two pronged strategy which we have classified into the standalone algorithm and the network algorithm. The standalone algorithm runs independently on each node of the network. It monitors the active processes on the node and tries to identify Bot processes using parameters such as response time and output to input traffic ratio. If a suspicious process has been identified the network algorithm is triggered. The network algorithm will then analyze conversations to and from the hosts of the network using the transport layer flow records. It then tries to deduce the Bot pattern as well as Bot signatures which can subsequently be used by the standalone algorithm to thwart Bot processes at their very onset.

cs.CR↗