Canada

This work studies the behaviors of two large-population teams competing in a discrete environment. The team-level interactions are modeled as a zero-sum game while the agent dynamics within each team is formulated as a collaborative mean-field team problem. Drawing inspiration from the mean-field literature, we first approximate the large-population team game with its infinite-population limit. Subsequently, we introduce two fictitious coordinators and transform the infinite-population game to an equivalent zero-sum game between the two coordinators. Via a novel reachability analysis, we study the optimal coordination strategies, which induce decentralized strategies under the original information structure. We establish the $\epsilon$-optimality of the resulting team strategies for the finite-population game, with the sub-optimality diminishing as the team size approaches infinity. The theoretical guarantees are verified by numerical examples.

AAAI 2024

Zero-Sum Games between Mean-Field Teams: Reachability-Based Analysis under Mean-Field Sharing

large-population games

adversarial agents

mean-field

multiagent systems

scalability

game theory

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

One of the major challenges of offline reinforcement learning (RL) is dealing with distribution shifts that stem from the mismatch between the trained policy and the data collection policy. Stationary distribution correction estimation algorithms (DICE) have addressed this issue by regularizing the policy optimization with f-divergence between the state-action visitation distributions of the data collection policy and the optimized policy. While such regularization naturally integrates to derive an objective to get optimal state-action visitation, such an implicit policy optimization framework has shown limited performance in practice. We observe that the reduced performance is attributed to the biased estimate and the properties of conjugate functions of f-divergence regularization. In this paper, we improve the regularized implicit policy optimization framework by relieving the bias and reshaping the conjugate function by relaxing the constraints. We show that the relaxation adjusts the degree of involvement of the sub-optimal samples in optimization, and we derive a new offline RL algorithm that benefits from the relaxed framework, improving from a previous implicit policy optimization algorithm by a large margin.

Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization

Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data without compromising privacy. Group fairness and client fairness are two dimensions of fairness that are important for FL. Standard FL can result in disproportionate disadvantages for certain clients, and it still faces the challenge of treating different groups equitably in a population. The problem of privately training fair FL models without compromising the generalization capability of disadvantaged clients remains open. In this paper, we propose a method, called mFairFL, to address this problem and achieve group fairness and client fairness simultaneously. mFairFL leverages differential multipliers to construct an optimization objective for empirical risk minimization with fairness constraints. Before aggregating locally trained models, it first detects conflicts among their gradients, and then iteratively curates the direction and magnitude of gradients to mitigate these conflicts. Theoretical analysis proves mFairFL facilitates the fairness in model development. The experimental evaluations based on three benchmark datasets show significant advantages of mFairFL compared to seven state-of-the-art baselines.

Multi-Dimensional Fair Federated Learning

Time-inconsistency is a characteristic of human behavior in which people plan for long-term benefits but take actions that differ from the plan due to conflicts with short-term benefits. Such time-inconsistent behavior is believed to be caused by present bias, a tendency to overestimate immediate rewards and underestimate future rewards. It is essential in behavioral economics to investigate the relationship between present bias and time-inconsistency. In this paper, we propose a model for analyzing agent behavior with present bias in tasks to make progress toward a goal over a specific period. Unlike previous models, the state sequence of the agent can be described analytically in our model. Based on this property, we analyze three crucial problems related to agents under present bias: task abandonment, optimal goal setting, and optimal reward scheduling. Extensive analysis reveals how present bias affects the condition under which task abandonment occurs and optimal intervention strategies. Our findings are meaningful for preventing task abandonment and intervening through incentives in the real world.

Analytically Tractable Models for Decision Making under Present Bias

Persistence diagrams (PD)s play a central role in topological data analysis, and are used in an ever increasing variety of applications. The comparison of PD data requires computing distances among large sets of PDs, with metrics which are accurate, theoretically sound, and fast to compute. Especially for denser multi-dimensional PDs, such comparison metrics are lacking. While on the one hand, Wasserstein-type distances have high accuracy and theoretical guarantees, they incur high computational cost. On the other hand, distances between vectorizations such as Persistence Statistics (PS)s have lower computational cost, but lack the accuracy guarantees and theoretical properties of a true distance over PD space. In this work we introduce a class of pseudodistances called Extended Topological Pseudodistances (ETD)s, which have tunable complexity, and can approximate Sliced and classical Wasserstein distances at the high-complexity extreme, while being computationally lighter and close to Persistence Statistics at the lower complexity extreme, and thus allow users to interpolate between the two metrics. We build theoretical comparisons to show how to fit our new distances at an intermediate level between persistence vectorizations and Wasserstein distances. We also experimentally verify that ETDs outperform PSs in terms of accuracy and outperform Wasserstein and Sliced Wasserstein distances in terms of computational complexity.

A Class of Topological Pseudodistances for Fast Comparison of Persistence Diagrams

We develop a model of content filtering as a game between the filter and the content consumer, where the latter incurs information costs for examining the content. Motivating examples include censoring misinformation, spam/phish filtering, and recommender systems acting on a stream of content. When the attacker is exogenous, we show that improving the filter’s quality is weakly Pareto improving, but has no impact on equilibrium payoffs until the filter becomes sufficiently accurate. Further, if the filter does not internalize the consumer’s information costs, its lack of commitment power may render it useless and lead to inefficient outcomes. When the attacker is also strategic, improvements in filter quality may decrease equilibrium payoffs.

Content Filtering with Inattentive Information Consumers | VIDEO

Thompson sampling (TS) has been known for its outstanding empirical performance supported by theoretical guarantees across various reward models in the classical stochastic multi-armed bandit problems.
Nonetheless, its optimality is often restricted to specific priors due to the common observation that TS is fairly insensitive to the choice of the prior when it comes to asymptotic regret bounds.
However, when the model contains multiple parameters, the optimality of TS highly depends on the choice of priors, which casts doubt on the generalizability of previous findings to other models. 
To address this gap, this study explores the impact of selecting noninformative priors, offering insights into the performance of TS when dealing with new models that lack theoretical understanding.
We first extend the regret analysis of TS to the model of uniform distributions with unknown supports, which would be the simplest non-regular model. 
Our findings reveal that changing noninformative priors can significantly affect the expected regret, aligning with previously known results in other multiparameter bandit models.
Although the uniform prior is shown to be optimal, we highlight the inherent limitation of its optimality, which is limited to specific parameterizations and emphasizes the significance of the invariance property of priors.
In light of this limitation, we propose a slightly modified TS-based policy, called TS with Truncation (TS-T), which can achieve the asymptotic optimality for the Gaussian models and the uniform models by using the reference prior and the Jeffreys prior that are invariant under one-to-one reparameterizations.
This policy provides an alternative approach to achieving optimality by employing fine-tuned truncation, which would be much easier than hunting for optimal priors in practice.

The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models

The conventional wisdom of simple models in signal processing and machine learning misses the bigger picture, especially over-parameterized neural networks (NNs), where the number of parameters are much larger than the number of training data. Our goal is to explore the mystery behind over-parameterized NNs from a theoretical side.

In this talk, I will discuss the role of over-parameterization in neural networks, to theoretically understand why they can perform well. First, I will discuss the role of over-parameterization in neural networks, to theoretically understand why they can perform well in terms of benign overfitting and double descent. Furthermore, I will talk about the robustness of neural networks, affected by architecture and initialization in a function space theory view. It aims to answer a fundamental question: over-parameterization in NNs helps or hurts robustness? Besides, from classical statistical learning to sequential decision making, I will talk about the benefits of over-parameterization on how deep reinforcement learning works well for function approximation. Potential future directions on theory of over-parameterization ML will also be discussed.

The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly

Recent works in artificial intelligence fairness attempt to mitigate discrimination by proposing constrained optimization programs that achieve parity for some fairness statistics. Most assume the availability of class label which is impractical in many real-world applications such as precision medicine, actuarial analysis and recidivism prediction. To this end, this talk revisits fairness and reveals idiosyncrasies of existing fairness literature assuming the availability of class label that limits their real-world utility. The primary artifacts are formulating fairness with censorship to account for scenarios where the class label is not guaranteed, and a suite of corresponding new fairness notions, algorithms, and theoretical constructs to bridge the gap between the design of a ``fair'' model in the lab and its deployment in the real-world.

Fairness with Censorship: Bridging the Gap between Fairness Research and Real-World Deployment | VIDEO

The increasingly decentralized and private nature of data in our digital society has  motivated the development of personalized, collaborative intelligent systems that enable knowledge aggregation across multiple data owners while accommodating for their data privacy and system constraints. However, collaborative learning has only been investigated in simple and limited settings: isolated task scenarios where learning begins from scratch and does not build on prior expertise; learned model is represented in task-specific forms which are not generalizable to unseen, emerging scenarios; and more often, a universal model representation is assumed across collaborators, ignoring their local compute constraints or input representations. This restricts its practicality in continual learning scenarios with limited task data, which demand continuous adaptation and knowledge transfer across different information silos, tasks, and learning models, as well as the utilization of prior solution expertises. To overcome these limitations, my research has been focused on developing effective and scalable resource-aware collaborative learning frameworks. The current progress and future directions of my research at Washington State University (WSU) are summarized in this letter.

--

As the system only allows a single PDF submission, my cover letter (2-page excluding references), my resume and the one-page statement of my talk (1-page excluding references) have been concatenated into a single file in that order. Both my Google scholar profile and webpage are included in my resume, which I also detail below:

Google scholar profile: https://scholar.google.com/citations?user=E-kZZeQAAAAJ&hl=en
Homepage: https://htnghia87.github.io/

Resource-Aware Collaborative Learning across Heterogeneous Systems

Interactive theorem provers (ITPs) are computer programs in which axioms and a conjecture are stated in a formal language, and a user provides the ITP with relatively high-level steps of a formal proof for the conjecture. Then, by invoking automated theorem provers, the ITP tries to generate low-level steps that fill the gaps between the steps provided by the user, thus forming a complete formal proof of the conjecture. The ITP also checks the entire formal proof against the axioms, thus confirming the soundness of all derivations in the formal proof.

In this talk, I will discuss the existing opportunities and potential benefits to applying ITPs to reason about and verify AI concepts, algorithms, and software. I will also discuss the challenges we have to being able to apply ITPs in AI and reap those benefits. I will do so by discussing a number of my previous projects on the application of ITPs to different AI concepts, algorithms, and software systems. These  projects span different areas of planning (classical planning, temporal planning, and planning under uncertainty) as well as algorithms with applications in algorithmic game theory, like general graph matching and online matching.

Downloads

Next from AAAI 2024

Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization

Similar lecture

Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization

Similar lecture

Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions

Downloads