arXiv subjects

Vaneet Aggarwal

Publications and source records attributed to Vaneet Aggarwal.

At least 73 records · Page 4Linked to original sources

arXiv2026

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted $K$ nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with $N\!\in\![11,16]$ pedestrians in a $3\mathrm{m}\times3\mathrm{m}$ arena and evaluated up to $N\!=\!21$ pedestrians ($1.3\times$ denser), our policy reaches the goal in $>99\%$ of episodes and achieves $86\%$ collision-free success in random crowds, with markedly less freezing than analytical methods and a $>\!60$-point collision-free margin over learning-based benchmark methods. Codes are available at \href{https://github.com/jznmsl/PSS-Social}{https://github.com/jznmsl/PSS-Social}.

cs.LG↗

arXiv2026

PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing

Recent advances in generative image editing have enabled transformative applications, from professional head shot generation to avatar stylization. However, these systems often require uploading high-fidelity facial images to third-party models, raising concerns around biometric privacy, data misuse, and user consent. We propose a privacy-preserving pipeline that supports high-quality editing while keeping users in control over their biometric data in face-centric use cases. Our approach separates identity-sensitive regions from editable image context using on-device segmentation and masking, enabling secure, user-controlled editing without modifying third-party generative models. Unlike traditional cloud-based tools, PRIVATEEDIT enforces privacy by default: biometric data is never exposed or transmitted. This design requires no access to or retraining of third-party models, making it compatible with a wide range of commercial APIs. By treating privacy as a core design constraint, our system supports responsible generative AI centered on user autonomy and trust. The pipeline includes a tunable masking mechanism that lets users control how much facial information is concealed, allowing them to balance privacy and output fidelity based on trust level or use case. We demonstrate its applicability in professional and creative workflows and provide a user interface for selective anonymization. By advocating privacy-by-design in generative AI, our work offers both technical feasibility and normative guidance for protecting digital identity. The source code is available at https://github.com/Dipeshtamboli/PrivateEdit-Privacy-Preserving-GenAI.

cs.CR↗

arXiv2026

Oracle-Robust Online Alignment for Large Language Models

We study online alignment of large language models under misspecified preference feedback, where the observed preference oracle deviates from an ideal but unknown ground-truth oracle. The online LLM alignment problem is a bi-level reinforcement problem due to the coupling between data collection and policy updates. Recently, the problem has been reduced to tractable single-level objective in the SAIL (Self-Improving Efficient Online Alignment) framework. In this paper, we introduce a pointwise oracle uncertainty set in this problem and formulate an oracle-robust online alignment objective as a worst-case optimization problem. For log-linear policies, we show that this robust objective admits an exact closed-form decomposition into the original loss function plus an explicit sensitivity penalty. We develop projected stochastic composite updates for the resulting weakly convex objective and prove $\widetilde{O}(\varepsilon^{-2})$ oracle complexity for reaching approximate stationarity.

cs.LG↗

arXiv2026

A Unified Framework for Analyzing Meta-algorithms in Online Convex Optimization

In this paper, we analyze the problem of online convex optimization in different settings, including different feedback types (full-information/semi-bandit/bandit/etc) in either stochastic or non-stochastic setting and different notions of regret (static adversarial regret/dynamic regret/adaptive regret). This is done through a framework which allows us to systematically propose and analyze meta-algorithms for the various settings described above. We show that any algorithm for online linear optimization with deterministic gradient feedback against fully adaptive adversaries is an algorithm for online convex optimization. We also show that any such algorithm that requires full-information feedback may be transformed to an algorithm with semi-bandit feedback with comparable regret bound. We further show that algorithms that are designed for fully adaptive adversaries using deterministic semi-bandit feedback can obtain similar bounds using only stochastic semi-bandit feedback when facing oblivious adversaries. We use this to describe general meta-algorithms to convert first order algorithms to zeroth order algorithms with comparable regret bounds. Our framework allows us to analyze online optimization in various settings, recovers several results in the literature with a simplified proof technique, and provides new results.

cs.LG↗

arXiv2026

Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedback

We study the \emph{Submodular Welfare Problem} (SWP), where items are partitioned among agents with monotone submodular utilities to maximize the total welfare under \emph{bandit feedback}. Classical SWP assumes full value-oracle access, achieving $(1-1/e)$ approximations via continuous-greedy algorithms. We extend this to a \emph{multi-agent combinatorial bandit} framework (\textsc{MA-CMAB}), where actions are partitions under full-bandit feedback with non-communicating agents. Unlike prior single-agent or separable multi-agent CMAB models, our setting couples agents through shared allocation constraints. We propose an explore-then-commit strategy with randomized assignments, achieving $\tilde{\mathcal{O}}(T^{2/3})$ regret against a $(1-1/e)$ benchmark, the first such guarantee for partition-based submodular welfare problem under bandit feedback.

cs.GT↗

arXiv2026

LiSFC-Search: Lifelong Search for Network SFC Optimization under Non-stationary Drifts

Edge-cloud convergence is reshaping service provisioning across 5G/6G and computing power networks (CPNs). Service function chaining (SFC) requires continuously placing and scheduling virtual network functions (VNFs) chains under compute/bandwidth and end-to-end QoS constraints. Most SFC optimizers assume static or stationary networks, and degrade under long-term topology/resource changes (failures, upgrades, expansions) that induce non-stationary graph drifts. We propose LiSFC, a Lipschitz lifelong planner that transfers MCTS statistics across drifting network configurations using an MDP-distance bound. More precisely, we formulate the problem as a sequence of MDPs indexed by the underlying network graph and constraints, and we define a \emph{graph drift} metric that upper-bounds the LiZero MDP distance. This allows LiSFC to import theoretical guarantees on bias and sample efficiency from the LiZero framework while being tailored to cloud-network convergence. We then design \emph{LiSFC-Search}, an SFC-aware unified MCTS (UMCTS) procedure that uses transferable adaptive UCT (aUCT) bonuses to reuse search statistics from prior CPN configurations. Preliminary results on synthetic CPN topologies and SFC workloads show that LiSFC consistently reduces SFC blocking probability and improves tail delay compared to non-transfer MCTS and purely learning-based baselines, highlighting its potential as an AI/ML building block for cloud-network convergence.

cs.NI↗

arXiv2026

On The Sample Complexity Bounds In Bilevel Reinforcement Learning

Bilevel reinforcement learning (BRL) has emerged as a powerful framework for aligning generative models, yet its theoretical foundations, especially sample complexity bounds, remain underexplored. In this work, we present the first sample complexity bound for BRL, establishing a rate of $\mathcal{O}(ε^{-3})$ in continuous state-action spaces. Traditional MDP analysis techniques do not extend to BRL due to its nested structure and non-convex lower-level problems. We overcome these challenges by leveraging the Polyak-Łojasiewicz (PL) condition and the MDP structure to obtain closed-form gradients, enabling tight sample complexity analysis. Our analysis also extends to general bi-level optimization settings with non-convex lower levels, where we achieve state-of-the-art sample complexity results of $\mathcal{O}(ε^{-3})$ improving upon existing bounds of $\mathcal{O}(ε^{-6})$. Additionally, we address the computational bottleneck of hypergradient estimation by proposing a fully first-order, Hessian-free algorithm suitable for large-scale problems.

cs.LG↗

arXiv2026

DART: aDaptive Accept RejecT for non-linear top-K subset identification

We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing among $\binom{N}{K}$ options, making the action space large. To simplify the problem, existing works on combinatorial bandits {typically} assume feedback as a linear function of individual rewards. In this paper, we prove the lower bound for top-$K$ subset selection with bandit feedback with possibly correlated rewards. We present a novel algorithm for the combinatorial setting without using individual arm feedback or requiring linearity of the reward function. Additionally, our algorithm works on correlated rewards of individual arms. Our algorithm, aDaptive Accept RejecT (DART), sequentially finds good arms and eliminates bad arms based on confidence bounds. DART is computationally efficient and uses storage linear in $N$. Further, DART achieves a regret bound of $\tilde{\mathcal{O}}(K\sqrt{KNT})$ for a time horizon $T$, which matches the lower bound in bandit feedback up to a factor of $\sqrt{\log{2NT}}$. When applied to the problem of cross-selling optimization and maximizing the mean of individual rewards, the performance of the proposed algorithm surpasses that of state-of-the-art algorithms. We also show that DART significantly outperforms existing methods for both linear and non-linear joint reward environments.

cs.LG↗

arXiv2026

Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on ergodicity or strong mixing-time assumptions, which fail to hold in the presence of transient states. We propose a primal--dual natural actor--critic algorithm that leverages multi-level Monte Carlo (MLMC) estimators and an explicit burn-in mechanism to handle unichain dynamics without requiring mixing-time oracles. Our analysis establishes finite-time regret and cumulative constraint violation bounds that scale as $\tilde{O}(\sqrt{T})$, up to approximation errors arising from policy and critic parameterization, thereby extending order-optimal guarantees to a significantly broader class of CMDPs.

cs.LG↗

arXiv2026

Sample Complexity Analysis for Constrained Bilevel Reinforcement Learning

Several important problem settings within the literature of reinforcement learning (RL), such as meta-learning, hierarchical learning, and RL from human feedback (RL-HF), can be modelled as bilevel RL problems. A lot has been achieved in these domains empirically; however, the theoretical analysis of bilevel RL algorithms hasn't received a lot of attention. In this work, we analyse the sample complexity of a constrained bilevel RL algorithm, building on the progress in the unconstrained setting. We obtain an iteration complexity of $O(ε^{-2})$ and sample complexity of $\tilde{O}(ε^{-4})$ for our proposed algorithm, Constrained Bilevel Subgradient Optimization (CBSO). We use a penalty-based objective function to avoid the issue of primal-dual gap and hyper-gradient in the context of a constrained bilevel problem setting. The penalty-based formulation to handle constraints requires analysis of non-smooth optimization. We are the first ones to analyse the generally parameterized policy gradient-based RL algorithm with a non-smooth objective function using the Moreau envelope.

cs.LG↗

arXiv2026

Stronger Approximation Guarantees for Non-Monotone γ-Weakly DR-Submodular Maximization

Maximizing submodular objectives under constraints is a fundamental problem in machine learning and optimization. We study the maximization of a nonnegative, non-monotone $γ$-weakly DR-submodular function over a down-closed convex body. Our main result is an approximation algorithm whose guarantee depends smoothly on $γ$; in particular, when $γ=1$ (the DR-submodular case) our bound recovers the $0.401$ approximation factor, while for $γ<1$ the guarantee degrades gracefully and, it improves upon previously reported bounds for $γ$-weakly DR-submodular maximization under the same constraints. Our approach combines a Frank-Wolfe-guided continuous-greedy framework with a $γ$-aware double-greedy step, yielding a simple yet effective procedure for handling non-monotonicity. This results in state-of-the-art guarantees for non-monotone $γ$-weakly DR-submodular maximization over down-closed convex bodies.

cs.LG↗

arXiv2025

Poisson wavefront imaging in photon-starved scenarios

Low-photon phase imaging is essential in applications where the signal is limited by short exposure times, faint targets, or the need to protect delicate samples. We address this challenge with Poisson Wavefront Imaging (PWI), an optimization-based method that incorporates Poisson photon statistics and a smoothness prior to improve wavefront reconstruction. By using multiple spatial light modulator's phase patterns, PWI enhances Fisher information, boosting theoretical accuracy and regularizing the retrieval process effectively. In simulations, PWI approaches the theoretical phase error limit, and in experiments it reduces phase error by up to 1.6x compared to the Gerchberg-Saxton algorithm, achieving 1.8x higher resolution wavefront imaging in low photon regime. This method advances photon-limited imaging with applications in astronomy, semiconductor metrology, and biological systems.

physics.optics↗

arXiv2025

Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning

We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asymptotic convergence guarantees, leaving open the question of sample complexity. In this work, we address this gap by showing that the robust Bellman operator is a contraction under a carefully constructed semi-norm, and developing a stochastic approximation framework with controlled bias. Our approach builds upon Multi-Level Monte Carlo (MLMC) techniques to estimate the robust Bellman operator efficiently. To overcome the infinite expected sample complexity inherent in standard MLMC, we introduce a truncation mechanism based on a geometric distribution, ensuring a finite expected sample complexity while maintaining a small bias that decays exponentially with the truncation level. Our method achieves the order-optimal sample complexity of $\tilde{\mathcal{O}}(ε^{-2})$ for robust policy evaluation and robust average reward estimation, marking a significant advancement in robust reinforcement learning theory.

stat.ML↗

arXiv2025

Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm

This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a high convergence rate. In particular, our algorithm achieves global convergence and constraint violation rates of $\tilde{\mathcal{O}}(1/\sqrt{T})$ over a horizon of length $T$ when the mixing time, $τ_{\mathrm{mix}}$, is known to the learner. In absence of knowledge of $τ_{\mathrm{mix}}$, the achievable rates change to $\tilde{\mathcal{O}}(1/T^{0.5-ε})$ provided that $T \geq \tilde{\mathcal{O}}\left(τ_{\mathrm{mix}}^{2/ε}\right)$. Our results match the theoretical lower bound for Markov Decision Processes and establish a new benchmark in the theoretical exploration of average reward CMDPs.

cs.LG↗

arXiv2025

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing empirical success, the theoretical understanding of flow matching remains limited, particularly in terms of sample complexity results. In this work, we provide the first analysis of the sample complexity for flow-matching based generative models without assuming access to the empirical risk minimizer (ERM) of the loss function for estimating the velocity field. Under standard assumptions on the loss function for velocity field estimation and boundedness of the data distribution, we show that a sufficiently expressive neural network can learn a velocity field such that with $\mathcal{O}(ε^{-4})$ samples, such that the Wasserstein-2 distance between the learned and the true distribution is less than $\mathcal{O}(ε)$. The key technical idea is to decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field. Each of these terms are then handled via techniques that may be of independent interest.

cs.LG↗

arXiv2025

ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions

We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz-continuous functions with unknown Lipschitz constants. Building on the Every Call is Precious (ECP) framework, which ensures that each accepted function evaluation is potentially informative, ECPv2 addresses key limitations of ECP, including high computational cost and overly conservative early behavior. ECPv2 introduces three innovations: (i) an adaptive lower bound to avoid vacuous acceptance regions, (ii) a Worst-m memory mechanism that restricts comparisons to a fixed-size subset of past evaluations, and (iii) a fixed random projection to accelerate distance computations in high dimensions. We theoretically show that ECPv2 retains ECP's no-regret guarantees with optimal finite-time bounds and expands the acceptance region with high probability. We further empirically validate these findings through extensive experiments and ablation studies. Using principled hyperparameter settings, we evaluate ECPv2 across a wide range of high-dimensional, non-convex optimization problems. Across benchmarks, ECPv2 consistently matches or outperforms state-of-the-art optimizers, while significantly reducing wall-clock time.

cs.LG↗

arXiv2025

Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPs

In this work, we study the problem of finding robust and safe policies in Robust Constrained Average-Cost Markov Decision Processes (RCMDPs). A key challenge in this setting is the lack of strong duality, which prevents the direct use of standard primal-dual methods for constrained RL. Additional difficulties arise from the average-cost setting, where the Robust Bellman operator is not a contraction under any norm. To address these challenges, we propose an actor-critic algorithm for Average-Cost RCMDPs. We show that our method achieves both $ε$-feasibility and $ε$-optimality, and we establish a sample complexities of $\tilde{O}\left(ε^{-4}\right)$ and $\tilde{O}\left(ε^{-6}\right)$ with and without slackness assumption, which is comparable to the discounted setting.

cs.LG↗

arXiv2025

GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

Spatial transcriptomics (ST) technologies can be used to align transcriptomes with histopathological morphology, presenting exciting new opportunities for biomolecular discovery. Using ST data, we construct a novel framework, GeneFlow, to map transcriptomics onto paired cellular images. By combining an attention-based RNA encoder with a conditional UNet guided by rectified flow, we generate high-resolution images with different staining methods (e.g. H&E, DAPI) to highlight various cellular/tissue structures. Rectified flow with high-order ODE solvers creates a continuous, bijective mapping between transcriptomics and image manifolds, addressing the many-to-one relationship inherent in this problem. Our method enables the generation of realistic cellular morphology features and spatially resolved intercellular interactions from observational gene expression profiles, provides potential to incorporate genetic/chemical perturbations, and enables disease diagnosis by revealing dysregulated patterns in imaging phenotypes. Our rectified flow-based method outperforms diffusion-based baseline method in all experiments. Code can be found at https://github.com/wangmengbo/GeneFlow.

q-bio.QM↗