You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 10 Nov 2023 • Emmanouil Angelis, Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Stefan Bauer

Furthermore, potential causes may be correlated in practical applications.

1 code implementation • 2 Oct 2023 • Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low

We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.

no code implementations • 21 Jun 2023 • Negin Golrezaei, Patrick Jaillet, Zijie Zhou

Specifically, in a C-Pareto optimal setting, we maximize the robust ratio while ensuring that the consistent ratio is at least C. Our proposed C-Pareto optimal algorithm is an adaptive protection level algorithm, which extends the classical fixed protection level algorithm introduced in Littlewood (2005) and Ball and Queyranne (2009).

no code implementations • 16 Jun 2023 • 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.

no code implementations • 12 Jun 2023 • Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer

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.

no code implementations • 14 Feb 2023 • Gauthier Guinet, Saurabh Amin, Patrick Jaillet

In this paper, we study both multi-armed and contextual bandit problems in censored environments.

no code implementations • 14 Feb 2023 • Moise Blanchard, Steve Hanneke, Patrick Jaillet

We show that optimistic universal learning for contextual bandits with adversarial rewards is impossible in general, contrary to all previously studied settings in online learning -- including standard supervised learning.

no code implementations • 9 Feb 2023 • Moïse Blanchard, Junhui Zhang, Patrick Jaillet

For the feasibility problem, in which an algorithm only has access to a separation oracle, we show a stronger trade-off: for at most $d^{2-\delta}$ memory, the number of queries required is $\tilde\Omega(d^{1+\delta})$.

no code implementations • 3 Feb 2023 • Yuan Deng, Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang, Vahab Mirrokni

In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem.

no code implementations • 31 Dec 2022 • Moise Blanchard, Steve Hanneke, Patrick Jaillet

Lastly, we consider the case of added continuity assumptions on rewards and show that these lead to universal consistency for significantly larger classes of data-generating processes.

1 code implementation • 13 Oct 2022 • Zhongxiang Dai, Yao Shu, Bryan Kian Hsiang Low, Patrick Jaillet

linear model), which is equivalently sampled from the GP posterior with the NTK as the kernel function.

no code implementations • 20 Aug 2022 • The Viet Bui, Tien Mai, Patrick Jaillet

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories.

1 code implementation • 14 Jun 2022 • Zhongxiang Dai, Yizhou Chen, Haibin Yu, Bryan Kian Hsiang Low, Patrick Jaillet

We prove that both algorithms are asymptotically no-regret even when some or all previous tasks are dissimilar to the current task, and show that RM-GP-UCB enjoys a better theoretical robustness than RM-GP-TS.

1 code implementation • 28 May 2022 • Zhongxiang Dai, Yao Shu, Arun Verma, Flint Xiaofeng Fan, Bryan Kian Hsiang Low, Patrick Jaillet

To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: $\text{UCB}^{a}$ allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while $\text{UCB}^{b}$ uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning.

no code implementations • 9 Mar 2022 • Moïse Blanchard, Patrick Jaillet

In addition, our analysis also provides a learning rule for mean estimation in general metric spaces that is consistent under adversarial responses without any moment conditions on the sequence, a result of independent interest.

no code implementations • 28 Feb 2022 • Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

Although the existing max-value entropy search (MES) is based on the widely celebrated notion of mutual information, its empirical performance can suffer due to two misconceptions whose implications on the exploration-exploitation trade-off are investigated in this paper.

no code implementations • 31 Dec 2021 • Tien Mai, Patrick Jaillet

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications.

1 code implementation • NeurIPS 2021 • Quoc Phong Nguyen, Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet

This paper presents two Bayesian optimization (BO) algorithms with theoretical performance guarantee to maximize the conditional value-at-risk (CVaR) of a black-box function: CV-UCB and CV-TS which are based on the well-established principle of optimism in the face of uncertainty and Thompson sampling, respectively.

no code implementations • NeurIPS 2021 • Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet

The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off.

1 code implementation • 30 Jul 2021 • Quoc Phong Nguyen, Zhaoxuan Wu, Bryan Kian Hsiang Low, Patrick Jaillet

Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function.

no code implementations • 13 May 2021 • Quoc Phong Nguyen, Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet

Value-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors.

no code implementations • 17 Apr 2021 • Haibin Yu, Dapeng Liu, Yizhou Chen, Bryan Kian Hsiang Low, Patrick Jaillet

Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart.

1 code implementation • 19 Dec 2020 • Quoc Phong Nguyen, Sebastian Tay, Bryan Kian Hsiang Low, Patrick Jaillet

This paper presents a novel approach to top-$k$ ranking Bayesian optimization (top-$k$ ranking BO) which is a practical and significant generalization of preferential BO to handle top-$k$ ranking and tie/indifference observations.

1 code implementation • 19 Dec 2020 • Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant.

no code implementations • NeurIPS 2020 • Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

We frame this problem as one of minimizing the Kullback-Leibler divergence between the approximate posterior belief of model parameters after directly unlearning from erased data vs. the exact posterior belief from retraining with remaining data.

1 code implementation • NeurIPS 2020 • Zhongxiang Dai, Kian Hsiang Low, Patrick Jaillet

Bayesian optimization (BO) is a prominent approach to optimizing expensive-to-evaluate black-box functions.

no code implementations • 16 Sep 2020 • Meghna Lowalekar, Pradeep Varakantham, Patrick Jaillet

The desired matching between resources and request groups is constrained by the edges between requests and request groups in this tripartite graph (i. e., a request can be part of at most one request group in the final assignment).

no code implementations • 13 Sep 2020 • Meghna Lowalekar, Pradeep Varakantham, Patrick Jaillet

This challenge has been addressed in existing work by: (i) generating as many relevant feasible (with respect to the available delay for customers) combinations of requests as possible in real-time; and then (ii) optimizing assignment of the feasible request combinations to vehicles.

no code implementations • 18 Aug 2020 • Tien Mai, Patrick Jaillet

We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP.

1 code implementation • 18 Aug 2020 • Youssef M. Aboutaleb, Moshe Ben-Akiva, Patrick Jaillet

We formulate the problem of learning an optimal nesting structure from the data as a mixed integer nonlinear programming (MINLP) optimization problem and solve it using a variant of the linear outer approximation algorithm.

no code implementations • ICML 2020 • Zhongxiang Dai, Yizhou Chen, Kian Hsiang Low, Patrick Jaillet, Teck-Hua Ho

This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff functions in repeated games, which we call Recursive Reasoning-Based BO (R2-B2).

no code implementations • 16 Nov 2019 • Tien Mai, Quoc Phong Nguyen, Kian Hsiang Low, Patrick Jaillet

We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories.

no code implementations • 16 Nov 2019 • Tien Mai, Kennard Chan, Patrick Jaillet

We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL).

no code implementations • 8 Nov 2019 • Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang

We show that this design allows the seller to control the number of periods in which buyers significantly corrupt their bids.

1 code implementation • NeurIPS 2019 • Haibin Yu, Yizhou Chen, Zhongxiang Dai, Kian Hsiang Low, Patrick Jaillet

This paper presents an implicit posterior variational inference (IPVI) framework for DGPs that can ideally recover an unbiased posterior belief and still preserve time efficiency.

no code implementations • 8 Jul 2019 • Dimitris Bertsimas, Arthur Delarue, Patrick Jaillet, Sebastien Martin

We propose a general optimization framework to create explanations for linear models.

no code implementations • 8 Jul 2019 • Dimitris Bertsimas, Arthur Delarue, Patrick Jaillet, Sebastien Martin

When quantitative models are used to support decision-making on complex and important topics, understanding a model's ``reasoning'' can increase trust in its predictions, expose hidden biases, or reduce vulnerability to adversarial attacks.

1 code implementation • 9 Aug 2018 • Itai Ashlagi, Maximilien Burq, Chinmoy Dutta, Patrick Jaillet, Amin Saberi, Chris Sholley

We study the problem of matching agents who arrive at a marketplace over time and leave after d time periods.

Data Structures and Algorithms

no code implementations • NeurIPS 2017 • Arthur Flajolet, Patrick Jaillet

We consider the problem of repeated bidding in online advertising auctions when some side information (e. g. browser cookies) is available ahead of submitting a bid in the form of a $d$-dimensional vector.

no code implementations • NeurIPS 2017 • Ofer Dekel, Arthur Flajolet, Nika Haghtalab, Patrick Jaillet

We show that the player can benefit from such a hint if the set of feasible actions is sufficiently round.

no code implementations • 1 Nov 2017 • Haibin Yu, Trong Nghia Hoang, Kian Hsiang Low, Patrick Jaillet

This paper presents a novel variational inference framework for deriving a family of Bayesian sparse Gaussian process regression (SGPR) models whose approximations are variationally optimal with respect to the full-rank GPR model enriched with various corresponding correlation structures of the observation noises.

no code implementations • 21 Nov 2016 • Chong Yang Goh, Patrick Jaillet

We propose a general approach for supervised learning with structured output spaces, such as combinatorial and polyhedral sets, that is based on minimizing estimated conditional risk functions.

no code implementations • 1 Mar 2016 • Swati Gupta, Michel Goemans, Patrick Jaillet

We give a general recipe to simulate the multiplicative weights update algorithm in time polynomial in their natural dimension.

no code implementations • NeurIPS 2015 • Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

By representing our IRL problem with a probabilistic graphical model, an expectation-maximization (EM) algorithm can be devised to iteratively learn the different reward functions and the stochastic transitions between them in order to jointly improve the likelihood of the expert’s demonstrated trajectories.

no code implementations • 21 Nov 2015 • Chun Kai Ling, Kian Hsiang Low, Patrick Jaillet

This paper presents a novel nonmyopic adaptive Gaussian process planning (GPP) framework endowed with a general class of Lipschitz continuous reward functions that can unify some active learning/sensing and Bayesian optimization criteria and offer practitioners some flexibility to specify their desired choices for defining new tasks/problems.

no code implementations • 20 Nov 2014 • Arthur Flajolet, Patrick Jaillet

In the convex optimization approach to online regret minimization, many methods have been developed to guarantee a $O(\sqrt{T})$ bound on regret for subdifferentiable convex loss functions with bounded subgradients, by using a reduction to linear loss functions.

no code implementations • 17 Nov 2014 • Kian Hsiang Low, Jiangbo Yu, Jie Chen, Patrick Jaillet

To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complementing a low-rank approximate representation of the full-rank GP based on a support set of inputs with a Markov approximation of the resulting residual process; the latter approximation is guaranteed to be closest in the Kullback-Leibler distance criterion subject to some constraint and is considerably more refined than that of existing sparse GP models utilizing low-rank representations due to its more relaxed conditional independence assumption (especially with larger data).

no code implementations • 9 Aug 2014 • Jie Chen, Kian Hsiang Low, Colin Keng-Yan Tan, Ali Oran, Patrick Jaillet, John Dolan, Gaurav Sukhatme

The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots.

no code implementations • 9 Aug 2014 • Jie Chen, Nannan Cao, Kian Hsiang Low, Ruofei Ouyang, Colin Keng-Yan Tan, Patrick Jaillet

We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.

no code implementations • NeurIPS 2013 • Asrar Ahmed, Pradeep Varakantham, Yossiri Adulyasak, Patrick Jaillet

Most robust optimization approaches for these problems have focussed on the computation of {\em maximin} policies which maximize the value corresponding to the worst realization of the uncertainty.

no code implementations • 24 May 2013 • Jie Chen, Nannan Cao, Kian Hsiang Low, Ruofei Ouyang, Colin Keng-Yan Tan, Patrick Jaillet

We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.