United States

Reinforcement Learning provides an attractive suite of online learning methods for personalizing interventions in Digital Behavioral Health. However, after a reinforcement learning algorithm has been run in a clinical study, how do we assess whether personalization occurred? We might find users for whom it appears that the algorithm has indeed learned in which contexts the user is more responsive to a particular intervention. But could this have happened completely by chance? We discuss some first approaches to addressing these questions

AAAI 2023

We used Reinforcement Learning; but did it work?

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

keynote

LiDAR-based 3D object detection is an indispensable task in advanced autonomous driving systems. Though impres- sive detection results have been achieved by superior 3D detectors, they suffer from significant performance degen- eration when facing unseen domains, such as different Li- DAR configurations, different cities, and weather conditions. The mainstream approaches tend to solve these challenges by leveraging unsupervised domain adaptation (UDA) tech- niques. However, these UDA solutions just yield unsatis- factory 3D detection results when there is a severe domain shift, e.g., from Waymo (64-beam) to nuScenes (32-beam). To address this, we present a novel Semi-Supervised Domain Adaptation method for 3D object detection (SSDA3D), where only a few labeled target data is available, yet can signif- icantly improve the adaptation performance. In particular, our SSDA3D includes an Inter-domain Adaptation stage and an Intra-domain Generalization stage. In the first stage, an Inter-domain Point-CutMix module is presented to efficiently align the point cloud distribution across domains. The Point- CutMix generates mixed samples of an intermediate domain, thus encouraging to learn domain-invariant knowledge. Then, in the second stage, we further enhance the model for better generalization on the unlabeled target set. This is achieved by exploring Intra-domain Point-MixUp in semi-supervised learning, which essentially regularizes the pseudo label dis- tribution. Experiments from Waymo to nuScenes show that, with only 10% labeled target data, our SSDA3D can surpass the fully-supervised oracle model with 100% target label. Our code is available at https://github.com/yinjunbo/SSDA3D.

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are state-of-the-art in modeling aleatoric uncertainty. The ensembles are created via sets of fixed dropout masks, making them less expensive than creating separate NF models. We demonstrate how to leverage the unique structure of NFs, base distributions, to estimate aleatoric uncertainty without relying on samples, provide a comprehensive set of baselines, and derive unbiased estimates for differential entropy. The methods were applied to a variety of experiments, commonly used to benchmark aleatoric and epistemic uncertainty estimation: 1D sinusoidal data, 2D windy grid-world (Wet Chicken), Pendulum, and Hopper. In these experiments, we setup an active learning framework and evaluate each model’s capability at measuring aleatoric and epistemic uncertainty. The results show the advantages of using NF ensembles in capturing complicated aleatoric while maintaining accurate epistemic uncertainty estimates.

Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling

Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixing augmentation strategies have advanced to generate the mixup mask to enrich the saliency information, which is a supervisory signal. However, these methods incur a significant computational burden to optimize the mixup mask. From this motivation, we propose a novel saliency-aware mixup method, GuidedMixup, which aims to retain the salient regions in mixup images with low computational overhead. We develop an efficient pairing algorithm that pursues to minimize the conflict of salient regions of paired images and achieve the rich saliency in mixup images. Moreover, GuidedMixup controls the mixup ratio for each pixel to better preserve the salient region by interpolating two paired images smoothly. The experiments on several datasets demonstrate that GuidedMixup provides a good trade-off between augmentation overhead and generalization performance on classification datasets. In addition, our method shows good performance in experiments with corrupted or reduced datasets.

GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps

We propose an enhanced semidefinite program (SDP) relaxation to enable the tight and efficient verification of neural networks (NNs). The tightness improvement is achieved by introducing a nonlinear constraint to existing SDP relaxations previously proposed for NN verification. The efficiency of the proposal stems from the iterative nature of the proposed algorithm in that it solves the resulting non-convex SDP by recursively solving auxiliary convex layer-based SDP problems. We show formally that the the solution generated by our algorithm is tighter than state-of-the-art SDP-based solutions for the problem. We also show that the solution sequence converges to the optimal solution of the non-convex enhanced SDP relaxation.  The experimental results on  standard benchmarks in the area show that our algorithm achieves the state-of-the-art performance 
whilst maintaining an acceptable computational cost.

Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification

Adversarial machine learning (AML) research is concerned with robustness of machine learning models and algorithms to malicious tampering. Originating at the intersection between machine learning and cybersecurity, AML has come to have broader research appeal, stretching traditional notions of security to include applications of computer vision, natural language processing, and network science. In addition, the problems of strategic classification, algorithmic recourse, and counterfactual explanations have essentially the same core mathematical structure as AML, despite distinct motivations. I give a simplified overview of the central problems in AML, and then discuss both the security-motivated AML domains, and the problems above unrelated to security. These together span a number of important AI subdisciplines, but can all broadly be viewed as concerned with trustworthy AI. My goal is to clarify both the technical connections among these, as
well as the substantive differences, suggesting directions for future research.

The Many Faces of Adversarial Machine Learning

AI systems can interact in unexpected ways, sometimes with disastrous consequences. As AI gets to control more of our world, these interactions will become more common and have higher stakes. As AI becomes more advanced, these interactions will become more sophisticated, and game theory will provide the tools for analyzing these interactions. However, AI agents are in some ways unlike the agents traditionally studied in game theory, introducing new challenges as well as opportunities. We propose a research agenda to develop the game theory of highly advanced AI agents, with a focus on achieving cooperation.

Foundations of Cooperative AI

The use of virtual agents (bots) has become essential for providing online assistance to customers. However, even though a lot of effort has been dedicated to the research, development, and deployment of such virtual agents, customers are frequently frustrated with the interaction with the virtual agent and require a human instead. We suggest that a holistic approach, combining virtual agents and human operators working together, is the path to providing satisfactory service. However, implementing such a holistic customer service system will not, and cannot, be achieved using any single AI technology or branch. Rather, such a system will inevitably require the integration of multiple and diverse AI technologies, including natural language processing, multi-agent systems, machine learning, reinforcement learning, and behavioral cloning; in addition to integration with other disciplines such as psychology, business, sociology, economics, operation research, informatics, computer-human interaction, and more. As such, we believe this customer service application offers a rich domain for experimentation and application of multidisciplinary AI. In this paper, we introduce the holistic customer service application and discuss the key AI technologies and disciplines required for a successful AI solution for this setting. For each of these AI technologies, we outline the key scientific questions and research avenues stemming from this setting. We demonstrate that integrating technologies from different fields can lead to a cost-effective successful customer service center. The challenge is that there is a need for several communities, each with its own language and modeling techniques, different problem-solving methods, and different evaluation methodologies, all of which need to work together. Real cooperation will require the formation of joint methodologies and techniques that could improve the service to customers, but, more importantly, open new directions in cooperation of diverse communities toward solving joint difficult tasks.

Customer Service Combining Human Operators and Virtual Agents:A Call for Multidisciplinary AI Research

How do we communicate with AI Agents that learn? One obvious answer is via language. Indeed, humans have evolved languages over tens of thousands of years to provide useful abstractions for understanding and interacting with each other and with the physical world. The claim advanced by some is that language influences how we think, what we perceive, how we focus our attention, and what we remember. We use language to capture and share our understanding of the world around us, to communicate high-level goals, intentions and objectives, and to support coordination with others. Importantly, language can provide us with useful and purposeful abstractions that can help us to generalize and transfer knowledge to new situations.

Language comes in many forms. In Computer Science and in the study of AI, we have historically used formal knowledge representation languages and programming languages to capture our understanding of the world and to communicate unambiguously with computers. In this talk I will discuss how formal language can help agents learn and reason with a deep dive on one particular topic – reinforcement learning. I’ll show how we can exploit the syntax and semantics of formal language and automata to aid in the specification of complex reward-worthy behavior, to improve the sample efficiency of learning, and to help agents learn what to remember. In doing so, formal language can help us address some of the challenges to reinforcement learning in the real world.

(Formal) Languages Help AI Agents Learn and Reason

Most work on scholarly document processing assumes that the information processed is trustworthy and factually correct. However, this is not always the case. There are two core challenges, which should be addressed: 1) ensuring that scientific publications are credible — e.g. that claims are not made without supporting evidence, and that all relevant supporting evidence is provided; and 2) that scientific findings are not misrepresented, distorted or outright misreported when communicated by journalists or the general public. In this talk, I will present some first steps towards addressing these problems, discussing our research on exaggeration detection, scientific fact checking, and on modelling information change in scientific communication more broadly.

Beyond Fact Checking — Modelling Information Change in Scientific Communication

I would like to propose an approach to the science of deep learning that roughly follows what physicists do to understand reality: (1) explore phenomena through controlled experiments, and (2) build theories based on toy mathematical models and non-fully- rigorous mathematical reasoning. I will illustrate (1) with the LEGO study (LEGO stands for Learning Equality and Group Operations), where we observe how transformers learn to solve simple linear systems of equations. I will also briefly illustrate (2) with an analysis of the emergence of threshold units when training a two-layers neural network to solve a simple sparse coding problem. The latter analysis connects to the recently discovered Edge of Stability phenomenon.

Based on joint works with Kwangjun Ahn, Arturs Backurs, Sinho Chewi Ronen Eldan, Suriya Gunasekar, Yin Tat Lee, Felipe Suarez, Tal Wagner, Yi Zhang, see arxiv.org/abs/2206.04301 and arxiv.org/abs/2212.07469.

Premium content

We used Reinforcement Learning; but did it work?

Downloads

Next from AAAI 2023

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

Similar lecture

Physics of AI — some first steps