arXiv subjects

Patrick Jaillet

Publications and source records attributed to Patrick Jaillet.

At least 19 recordsLinked to original sources

arXiv2026

Exact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-Leader

Online gradient descent is usually studied through external regret, where the learner competes with fixed alternatives. Recent work shows that first-order methods control richer action-dependent deviations. We ask for a geometric characterization of the deviations with respect to which online gradient descent, mirror descent, and follow-the-regularized-leader (FTRL) achieve no regret. We identify exactness as the common principle. Exactness means that the relevant displacement field is generated by a scalar potential, or equivalently that the associated one-form is exact in the geometry used by the algorithm. This geometry depends on the algorithm. For gradient descent it is Euclidean geometry, for mirror descent it is the geometry induced by the regularizer, and for FTRL it is the cumulative dual state. Under mild regularity conditions, exactness yields sublinear regret, while nonzero circulation provides the complementary obstruction and leads to linear regret. This gives a unified geometric framework for understanding the deviation classes controlled by these algorithms and reveals that different first-order methods can control genuinely different classes of deviations. These deviation classes have direct consequences for learning, particularly in games. We study the equilibrium notions induced by exact-form deviations and introduce conservative correlated equilibrium, reflecting both the conservative geometry of the underlying displacement fields and the restricted family of deviations available to the players. We characterize its relation to correlated equilibrium, determine when the resulting equilibrium notions coincide and when they separate, and show how these relationships depend on the geometry and the learning algorithm. Overall, this work gives a unified geometric account of what first-order online learning algorithms are no-regret with respect to, beyond fixed comparators.

cs.LG↗

arXiv2026

Efficient Learning and Symmetry Discovery under Exact Invariances

Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understood. Even for classical supervised regression settings, it has been unclear whether one can efficiently compute a regression function that is exactly invariant to a given group action. Recent work showed that exact invariance can be enforced in polynomial time when the underlying group is finite and known, but left open the cases of infinite groups and unknown symmetries. In this paper, we resolve both challenges. First, we present the first polynomial-time algorithm for learning with exact group invariances that applies uniformly to finite and infinite groups. The runtime is polynomial in the data dimension and sample size, and independent of the group, while achieving strong generalization guarantees. This provides a computational explanation for the empirical success of invariant and equivariant methods in geometric machine learning and partially answers a recent open question in the literature. Second, we study learning in the symmetry discovery setting, where the invariance group is unknown. Focusing on the subgroup lattice of a finite group, we show that exact symmetries can be identified from data and exploited for learning in polynomial time. For regression over finite-dimensional feature spaces, our algorithm provably recovers the underlying symmetry, matches the minimax-optimal sample complexity of the known-symmetry setting, and runs in time polynomial in the data dimension and sample size. Our analysis relies on tools from random Cayley graphs and expander theory, which may be of independent interest.

cs.LG↗

arXiv2026

Algorithmic Optimality Guarantees for Nonsmooth $H_\infty$ Output-Feedback Policy Search

We study continuous-time full-order dynamic output-feedback $H_\infty$ policy search, a nonconvex and nonsmooth problem. Direct policy search is a central paradigm in reinforcement learning and continuous control, but rigorous guarantees remain scarce in robust output-feedback settings. The $H_\infty$ problem is a canonical benchmark because it captures disturbance attenuation and robustness while exposing the hard nonsmooth geometry of policy-space optimization. We prove that on the exact identity-gauge slice of the extended convex lift, $\varepsilon$-stationarity yields $O(\varepsilon)$-suboptimality on compact exact slices, which in turn yields convergence-rate guarantees for nonsmooth policy-search methods. This result addresses the finite-time optimality-gap question raised by Guo and Hu [2022] in the more general dynamic output-feedback $H_\infty$ policy-search setting. We further use the established value equivalence supplied by extended convex lifting to formulate a nonstrict-feasibility bisection method with one final strict-feasibility recovery step, yielding an explicit $\varepsilon$-optimal stabilizing controller. These results provide a quantitative and algorithmic strengthening of prior qualitative optimality theory for nonsmooth $H_\infty$ policy search.

math.OC↗

arXiv2026

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts

Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical significance, this problem remains poorly understood under realistic conditions like adversarial queries, bandit feedback, and limited observability of models. We formalize embedding model routing as an adversarial contextual linear bandit with low-rank experts, where contexts are queries, actions are items, and experts are the embedding models working on low-rank latent representation spaces. We first establish that standard regret notions suffer from structural misspecification or statistical intractability, and we identify a log-quadratic policy class that is expressive enough to capture query-dependent model routing, yet structured enough to allow efficient online learning. Second, we propose a policy gradient algorithm called Hypentropy Policy Gradient (HPG). It provably adapts to the unknown low-rank structure under incomplete information and attains $\tilde{\mathcal O}(s\sqrt{M T})$ linearized policy regret -- where $s, M$, and $T$ are the intrinsic rank of the experts, the number of models, and the number of rounds -- thus avoiding a curse of dimensionality. Finally, we also provide an computationally efficient and parameter-free implementation of HPG.

cs.LG↗

arXiv2026

Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning

Collaborative machine learning involves training high-quality models using datasets from a number of sources. To incentivize sources to share data, existing data valuation methods fairly reward each source based on its data submitted as is. However, as these methods do not verify nor incentivize data truthfulness, the sources can manipulate their data (e.g., by submitting duplicated or noisy data) to artificially increase their valuations and rewards or prevent others from benefiting. This paper presents the first mechanism that provably ensures (F) collaborative fairness and incentivizes (T) truthfulness at equilibrium for Bayesian models. Our mechanism combines semivalues (e.g., Shapley value), which ensure fairness, and a truthful data valuation function (DVF) based on a validation set that is unknown to the sources. As semivalues are influenced by others' data, we introduce an additional condition to prove that a source can maximize its expected data values in coalitions and semivalues by submitting a dataset that captures its true knowledge. Additionally, we discuss the implications and suitable relaxations of (F) and (T) when the mediator has a limited budget for rewards or lacks a validation set. Our theoretical findings are validated on synthetic and real-world datasets.

cs.LG↗

arXiv2026

End-to-End Learning of Correlated Operating Reserve Requirements in Security-Constrained Economic Dispatch

Operating reserve requirements in security-constrained economic dispatch (SCED) depend strongly on the assumed correlation structure of renewable forecast errors, yet that structure is usually specified exogenously rather than learned for the dispatch task itself. This paper formulates correlated reserve-set design as an end-to-end trainable robust optimization problem: choose the ellipsoidal uncertainty-set shape to minimize robust dispatch cost subject to a target coverage requirement. By profiling the coverage constraint into a shape-dependent radius, the original bilevel problem becomes a single-stage differentiable objective, and KKT/dual information from the SCED solve provides task gradients without differentiating through the solver. For unknown distributions, a four-way train/tune/calibrate/test split combines a smoothed quantile-sensitivity estimator for training with split conformal calibration for deployment, yielding finite-sample marginal coverage under exchangeability and a consistent gradient estimator for the smoothed objective. The same task gradient can also be passed upstream to context-dependent encoders, which we report as a secondary extension. The framework is evaluated on the IEEE~118-bus system with a coupled SCED formulation that includes inter-zone transfer constraints. The learned static ellipsoid reduces dispatch cost by about 4.8\% relative to the Sample Covariance baseline while maintaining empirical coverage above the target level.

math.OC↗

arXiv2026

A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming

We study nonstationary Online Linear Programming (OLP), where $n$ orders arrive sequentially with reward-resource consumption pairs that form a sequence of independent, but not necessarily identically distributed, random vectors. At the beginning of the planning horizon, the decision-maker is provided with a resource endowment that is sufficient to fulfill a significant portion of the requests. The decision-maker seeks to maximize the expected total reward by making immediate and irrevocable acceptance or rejection decisions for each order, subject to this resource endowment. We focus on the challenging single-sample setting, where only one sample from each of the $n$ distributions is available at the start of the planning horizon. We propose a novel re-solving algorithm that integrates a dynamic programming perspective with the dual-based frameworks traditionally employed in stationary environments. In the large-resource regime, where the resource endowment scales linearly with the number of orders, we prove that our algorithm achieves $O((\log n)^2)$ regret across a broad class of nonstationary distribution sequences. Our results demonstrate that polylogarithmic regret is attainable even under significant environmental shifts and minimal data availability, bridging the gap between stationary OLP and more volatile real-world resource allocation problems.

cs.DS↗

arXiv2026

Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise

Towards understanding the statistical complexity of learning from heterogeneous sources, we study the problem of multi-distribution learning. Given $k$ data sources, the goal is to output a classifier for each source by exploiting shared structure to reduce sample complexity. We focus on the bounded label noise setting to determine whether the fast $1/\epsilon$ rates achievable in single-task learning extend to this regime with minimal dependence on $k$. Surprisingly, we show that this is not the case. We demonstrate that learning across $k$ distributions inherently incurs slow rates scaling with $k/\epsilon^2$, even under constant noise levels, unless each distribution is learned separately. A key technical contribution is a structured hypothesis-testing framework that captures the statistical cost of certifying near-optimality under bounded noise-a cost we show is unavoidable in the multi-distribution setting. Finally, we prove that when competing with the stronger benchmark of each distribution's optimal Bayes error, the sample complexity incurs a \textit{multiplicative} penalty in $k$. This establishes a \textit{statistical} separation between random classification noise and Massart noise, highlighting a fundamental barrier unique to learning from multiple sources.

stat.ML↗

arXiv2026

A Two-Layer Framework for Joint Online Configuration Selection and Admission Control

We study online configuration selection with admission control problem, which arises in LLM serving, GPU scheduling, and revenue management. In a planning horizon with $T$ periods, we consider a two-layer framework for the decisions made within each time period. In the first layer, the decision maker selects one of the $K$ configurations (ex. quantization, parallelism, fare class) which induces distribution over the reward-resource pair of the incoming request. In the second layer, the decision maker observes the request and then decides whether to accept it or not. Benchmarking this framework requires care. We introduce a \textbf{switching-aware fluid oracle} that accounts for the value of mixing configurations over time, provably upper-bounding any online policy. We derive a max-min formulation for evaluating the benchmark, and we characterize saddle points of the max-min problem via primal-dual optimality conditions linking equilibrium, feasibility, and complementarity. This guides the design of \textbf{SP-UCB--OLP} algorithm, which solves an optimistic saddle point problem and achieves $\tilde{O}(\sqrt{KT})$ regret.

math.OC↗

arXiv2026

Choice-Model-Assisted Q-learning for Delayed-Feedback Revenue Management

We study reinforcement learning for revenue management with delayed feedback, where a substantial fraction of value is determined by customer cancellations and modifications observed days after booking. We propose \emph{choice-model-assisted RL}: a calibrated discrete choice model is used as a fixed partial world model to impute the delayed component of the learning target at decision time. In the fixed-model deployment regime, we prove that tabular Q-learning with model-imputed targets converges to an $O(\varepsilon/(1-\gamma))$ neighborhood of the optimal Q-function, where $\varepsilon$ summarizes partial-model error, with an additional $O(t^{-1/2})$ sampling term. Experiments in a simulator calibrated from 61{,}619 hotel bookings (1{,}088 independent runs) show: (i) no statistically detectable difference from a maturity-buffer DQN baseline in stationary settings; (ii) positive effects under in-family parameter shifts, with significant gains in 5 of 10 shift scenarios after Holm--Bonferroni correction (up to 12.4\%); and (iii) consistent degradation under structural misspecification, where the choice model assumptions are violated (1.4--2.6\% lower revenue). These results characterize when partial behavioral models improve robustness under shift and when they introduce harmful bias.

cs.LG↗

arXiv2025

Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation

We study the dynamic allocation of indivisible resources to strategic agents under long-term constraints, where the planner aims to maximize social welfare, satisfy multiple constraints, and elicit near-truthful reports. We find standard primal-dual methods fragile in this setting: agents easily manipulate their reports to distort dual variables, sacrificing social efficiency for individual utility. To address this, we propose the Incentive-Aware Primal-Dual (IAPD) framework. On the primal side, we integrate three components to suppress manipulation: a VCG-based payment neutralizes immediate misreporting benefits, while epoch-based lazy updates and random exploration together ensure potential future gains are outweighed by immediate penalties. On the dual side, to overcome a learning barrier due to lazy updates -- which we call the "price of incentives" -- we design a novel optimistic online learning algorithm, O-FTRL-FP. It utilizes a fixed-point oracle to resolve the circular dependency between optimistic dual variables and the resulting allocations. Ultimately, our mechanism attains $\tilde{\mathcal O}(\sqrt T)$ social welfare regret, satisfies all long-term constraints, and induces a near-truthful equilibrium. It also smoothly generalizes to multi-unit multi-demand allocation problems. Notably, this $\tilde{\mathcal O}(\sqrt T)$ regret near-matches the non-strategic $\Omega(\sqrt T)$ lower bound, demonstrating that incentive-awareness can be accommodated at nearly no cost.

cs.GT↗

arXiv2025

Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization

We propose two variants of the Primal Dual Hybrid Gradient (PDHG) algorithm for saddle point problems with block decomposable duals, hereafter called Multi-Timescale PDHG (MT-PDHG) and its accelerated variant (AMT-PDHG). Through novel mixtures of Bregman divergence and multi-timescale extrapolations, our MT-PDHG and AMT-PDHG converge under arbitrary updating rates for different dual blocks while remaining fully deterministic and robust to extreme delays in dual updates. We further apply our (A)MT-PDHG, augmented with the gradient sliding techniques introduced in Lan et al. (2020), Lan (2016), to distributed optimization. The flexibility in choosing different updating rates for different blocks allows a more refined control over the communication rounds between different pairs of agents, thereby improving the efficiencies in settings with heterogeneity in local objectives and communication costs. Moreover, with careful choices of penalty levels, our algorithms show linear and thus optimal dependency on function similarities, a measure of how similar the gradients of local objectives are. This provides a positive answer to the open question whether such dependency is achievable for non-smooth objectives (Arjevani and Shamir 2015).

math.OC↗

arXiv2025

Efficient Online Mirror Descent Stochastic Approximation for Multi-Stage Stochastic Programming

We study the unconstrained and the minimax saddle point variants of the convex multi-stage stochastic programming problem, where consecutive decisions are coupled through the objective functions, rather than through the constraints. We approach the problems from the infinite-dimensional policy perspective, but consider an online setting where only the policies corresponding to the actual realization of the underlying stochastic process is needed. This leads to a trackable formulation, where the dimension of the output is linear in the number of stages $T$. We propose hypothetical Mirror Descent Stochastic Approximation (MDSA) for the infinite dimensional policies using stochastic conditional gradients. By taking advantage of the decomposability of the updates across stages and realizations of the underlying stochastic process, we show that the proposed MDSA algorithms admit efficient online implementation, which achieves overall gradient complexity linear in $T$, improving exponentially over all existing algorithms.

math.OC↗

arXiv2025

Learning with Exact Invariances in Polynomial Time

We study the statistical-computational trade-offs for learning with exact invariances (or symmetries) using kernel regression. Traditional methods, such as data augmentation, group averaging, canonicalization, and frame-averaging, either fail to provide a polynomial-time solution or are not applicable in the kernel setting. However, with oracle access to the geometric properties of the input space, we propose a polynomial-time algorithm that learns a classifier with \emph{exact} invariances. Moreover, our approach achieves the same excess population risk (or generalization error) as the original kernel regression problem. To the best of our knowledge, this is the first polynomial-time algorithm to achieve exact (not approximate) invariances in this context. Our proof leverages tools from differential geometry, spectral theory, and optimization. A key result in our development is a new reformulation of the problem of learning under invariances as optimizing an infinite number of linearly constrained convex quadratic programs, which may be of independent interest.

cs.LG↗

arXiv2025

Non-Monetary Mechanism Design without Priors: Achieving Efficiency via Adaptive Costly Audits

We study repeated resource allocation with strategic agents, where monetary transfers are disallowed and the planner has no prior information on agents' utility distributions. Inspired by the costly state verification literature, we assume the planner can request costly audits on the winning agent after allocation, revealing their true utility but without the ability to revoke the allocation. We design a mechanism achieving $T$-independent $\mathcal O(K^2)$ regret in social welfare while requesting $\mathcal O(K^3 \log T)$ audits in expectation, where $K$ is the number of agents and $T$ is the number of rounds. We further show an $\Omega(K)$ lower bound on the regret and an $\Omega(1)$ lower bound on the number of audits required for low regret. We also generalize our mechanism and analysis to imperfect audit models. Algorithmically, we show that incentivizing truthful behavior relies on accurately estimating agents' truthful winning probability online. To achieve this, we impose future punishments via adaptive audits; we also introduce an incentive-aligned flagging component allowing agents to flag biased estimates, which we prove is in their best interest. Analytically, without distributional information, the revelation principle cannot dictate a truth-telling equilibrium. Instead, we characterize a Perfect Bayesian Equilibrium via a reduction to an auxiliary game with only benign strategies. The technical tools developed herein can be of independent interest for other robust mechanism design problems where the revelation principle is inapplicable.

cs.GT↗

arXiv2025

Online Scheduling for LLM Inference with KV Cache Constraints

Large Language Model (LLM) inference, where a trained model generates text one word at a time in response to user prompts, is a computationally intensive process requiring efficient scheduling to optimize latency and resource utilization. A key challenge in LLM inference is the management of the Key-Value (KV) cache, which reduces redundant computations but introduces memory constraints. In this work, we model LLM inference with KV cache constraints theoretically and propose a novel batching and scheduling algorithm that minimizes inference latency while effectively managing the KV cache's memory. More specifically, we make the following contributions. First, to evaluate the performance of online algorithms for scheduling in LLM inference, we introduce a hindsight optimal benchmark, formulated as an integer program that computes the minimum total inference latency under full future information. Second, we prove that no deterministic online algorithm can achieve a constant competitive ratio when the arrival process is arbitrary. Third, motivated by the computational intractability of solving the integer program at scale, we propose a polynomial-time online scheduling algorithm and show that under certain conditions it can achieve a constant competitive ratio. We also demonstrate our algorithm's strong empirical performance by comparing it to the hindsight optimal in a synthetic dataset. Finally, we conduct empirical evaluations on a real-world public LLM inference dataset, simulating the Llama2-70B model on A100 GPUs, and show that our algorithm significantly outperforms the benchmark algorithms. Overall, our results offer a path toward more sustainable and cost-effective LLM deployment.

cs.LG↗

arXiv2024

Near-Optimal Mechanisms for Resource Allocation Without Monetary Transfers

We study the problem in which a central planner sequentially allocates a single resource to multiple strategic agents using their utility reports at each round, but without using any monetary transfers. We consider general agent utility distributions and two standard settings: a finite horizon $T$ and an infinite horizon with $\gamma$ discounts. We provide general tools to characterize the convergence rate between the optimal mechanism for the central planner and the first-best allocation if true agent utilities were available. This heavily depends on the utility distributions, yielding rates anywhere between $1/\sqrt T$ and $1/T$ for the finite-horizon setting, and rates faster than $\sqrt{1-\gamma}$, including exponential rates for the infinite-horizon setting as agents are more patient $\gamma\to 1$. On the algorithmic side, we design mechanisms based on the promised-utility framework to achieve these rates and leverage structure on the utility distributions. Intuitively, the more flexibility the central planner has to reward or penalize any agent while incurring little social welfare cost, the faster the convergence rate. In particular, discrete utility distributions typically yield the slower rates $1/\sqrt T$ and $\sqrt{1-\gamma}$, while smooth distributions with density typically yield faster rates $1/T$ (up to logarithmic factors) and $1-\gamma$.

cs.GT↗

arXiv2024

Neural Dueling Bandits: Preference-Based Optimization with Human Feedback

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However, existing algorithms assume the reward function is linear, which can be complex and non-linear in many real-life applications like online recommendations or ranking web search results. To overcome this challenge, we use a neural network to estimate the reward function using preference feedback for the previously selected arms. We propose upper confidence bound- and Thompson sampling-based algorithms with sub-linear regret guarantees that efficiently select arms in each round. We also extend our theoretical results to contextual bandit problems with binary feedback, which is in itself a non-trivial contribution. Experimental results on the problem instances derived from synthetic datasets corroborate our theoretical results.

cs.LG↗