5 citations · 37 across the 41 of their papers we have counts for
42 papers
Exact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-Leader
Ashkan Soleymani, Gabriele Farina, Patrick Jaillet
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 ac…
Efficient Learning and Symmetry Discovery under Exact Invariances
Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet +1
Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understood. Even for classical superv…
Algorithmic Optimality Guarantees for Nonsmooth Output-Feedback Policy Search
Ashkan Soleymani, Patrick Jaillet
We study continuous-time full-order dynamic output-feedback policy search, a nonconvex and nonsmooth problem. Direct policy search is a central paradigm in reinforcement…
Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
Yan Dai, Negin Golrezaei, Patrick Jaillet
Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical significance, this problem remains poorly…
Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation
Yan Dai, Negin Golrezaei, Patrick Jaillet
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 constr…
Learning with Exact Invariances in Polynomial Time
Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka +1
We study the statistical-computational trade-offs for learning with exact invariances (or symmetries) using kernel regression. Traditional methods, such as data augmentation, group…
Non-Monetary Mechanism Design without Priors: Achieving Efficiency via Adaptive Costly Audits
Yan Dai, Moise Blanchard, Patrick Jaillet
We study repeated resource allocation with strategic agents, where monetary transfers are disallowed and the planner has no prior information on agents' utility distributions. Insp…
Online Scheduling for LLM Inference with KV Cache Constraints
Patrick Jaillet, Jiashuo Jiang, Konstantina Mellou +3
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 efficien…
Near-Optimal Mechanisms for Resource Allocation Without Monetary Transfers
Moïse Blanchard, Patrick Jaillet
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 a…
Neural Dueling Bandits: Preference-Based Optimization with Human Feedback
Arun Verma, Zhongxiang Dai, Xiaoqiang Lin +2
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 ov…
A Universal Class of Sharpness-Aware Minimization Algorithms
Behrooz Tahmasebi, Ashkan Soleymani, Dara Bahri +2
Recently, there has been a surge in interest in developing optimization algorithms for overparameterized models as achieving generalization is believed to require algorithms with s…
Prompt Optimization with Human Feedback
Xiaoqiang Lin, Zhongxiang Dai, Arun Verma +3
Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performance of LLMs heavily depends on the input prompt, which has given rise…
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai +5
Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of in-context learning (ICL) allows us to adapt an LLM to downstream task…
Incentives in Private Collaborative Machine Learning
Rachael Hwee Ling Sim, Yehong Zhang, Trong Nghia Hoang +3
Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and rew…
When Should you Offer an Upgrade: Online Upgrading Mechanisms for Resource Allocation
Patrick Jaillet, Chara Podimata, Andrew Vakhutinsky +1
In this work, we study an upgrading scheme for online resource allocation problems. We work in a sequential setting, where at each round a request for a resource arrives and the de…
Grace Period is All You Need: Individual Fairness without Revenue Loss in Revenue Management
Patrick Jaillet, Chara Podimata, Zijie Zhou
Imagine you and a friend purchase identical items at a store, yet only your friend received a discount. Would your friend's discount make you feel unfairly treated by the store? An…
Information Design for Hybrid Work under Infectious Disease Transmission Risk
Sohil Shah, Saurabh Amin, Patrick Jaillet
We study a planner's provision of information to manage workplace occupancy when strategic workers (agents) face risk of infectious disease transmission. The planner implements an…
Batch Bayesian Optimization for Replicable Experimental Design
Zhongxiang Dai, Quoc Phong Nguyen, Sebastian Shenghong Tay +4
Many real-world experimental design problems (a) evaluate multiple experimental conditions in parallel and (b) replicate each condition multiple times due to large and heteroscedas…
Double Machine Learning Based Structure Identification from Temporal Data
Emmanouil Angelis, Francesco Quinzan, Ashkan Soleymani +2
Learning the causes of time-series data is a fundamental task in many applications, spanning from finance to earth sciences or bio-medical applications. Common approaches for this…
Quantum Bayesian Optimization
Zhongxiang Dai, Gregory Kang Ruey Lau, Arun Verma +3
Kernelized bandits, also known as Bayesian optimization (BO), has been a prevalent method for optimizing complicated black-box reward functions. Various BO algorithms have been the…
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai +5
Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. However, the performances of LLM…
DRCFS: Doubly Robust Causal Feature Selection
Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet +2
Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science. Existing approaches are often…
Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes
Moïse Blanchard, Junhui Zhang, Patrick Jaillet
We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization. Precise…
Online Resource Allocation with Convex-set Machine-Learned Advice
Negin Golrezaei, Patrick Jaillet, Zijie Zhou
Decision-makers often have access to machine-learned predictions about future demand that can help guide online resource allocation decisions. However, such predictions may be inac…