Join us for fun and relaxation at the beach. Learn to surf with experienced instructors or enjoy a yoga session to stretch and clear your mind. Mingle with other ICML attendees and make new friends. Contact: arnoldliwanaghawaii@gmail.com For more details and to sign up visit: Signup Form.

Given the success of AdvML-inspired research, we propose a new edition from our workshop at ICML’22 (AdvML-Frontiers’22), ‘The 2nd Workshop on New Frontiers in AdvML’ (AdvML-Frontiers’23). We target a high-quality international workshop, coupled with new scientific activities, networking opportunities, and enjoyable social events. Scientifically, we aim to identify the challenges and limitations of current AdvML methods and explore new prospective and constructive views for next-generation AdvML across the full theory/algorithm/application stack. As the sequel to AdvML-Frontiers’22, we will continue exploring the new frontiers of AdvML in theoretical understanding, scalable algorithm and system designs, and scientific development that transcends traditional disciplinary boundaries. We will also add new features and programs in 2023. First, we will expand existing research themes, particularly considering the popularity of large foundational models (e.g., DALL-E 2, Stable Diffusion, and ChatGPT). Examples of topics include AdvML for prompt learning, counteracting AI-synthesized fake images and texts, debugging ML from unified data-model perspectives, and ‘green’ AdvML towards environmental sustainability. Second, we will organize a new section, AI Trust in Industry, by inviting industry experts to introduce the practical trend of AdvML, technological innovations, products, and societal impacts (e.g., AI’s responsibility). Third, we will host a Show-and-Tell Demos in the poster session to allow demonstrations of innovations done by research and engineering groups in the industry, academia, and government entities. Fourth, we will collaborate with ‘Black in AI’ (where Co-Organizer Dr. Sanmi Koyejo is serving as the president) to increase the presence and inclusion of Black people in the field of AdvML by creating spaces for sharing ideas and networking.

Theory of Mind (ToM) is the ability to reason about the minds of other agents. The main theme of our workshop is the computational modeling of ToM, with a special focus on the role of natural language in such modeling. Specifically, ToM 2023 pays attention to cognitive foundations and theories of ToM, the acquisition and relationship between language and ToM, leveraging ToM to improve and explain NLP and ML models, and using ToM for positive social impact. This workshop intends to promote the community of researchers that are interested in improving the ability of intelligent agents to reason about others' mental states. Our proposed program provides a space to discuss pathways for understanding and applying ToM in psycholinguistics, pragmatics, human value alignment, social good, model explainability, and many other areas of NLP. ToM 2023 will be a full-day hybrid in-person/virtual workshop with several keynote speeches, and oral/poster/spotlight presentations, followed by a breakout discussion, panel discussion, and best paper award announcement. We also intend to host a mentoring program to broaden participation from a diverse set of researchers.

The Synergy of Scientific and Machine Learning Modeling Workshop (“SynS & ML”) is an interdisciplinary forum for researchers and practitioners interested in the challenges of combining scientific and machine-learning models. The goal of the workshop is to gather together machine learning researchers eager to include scientific models into their pipelines, domain experts working on augmenting their scientific models with machine learning, and researchers looking for opportunities to incorporate ML in widely-used scientific models.

The power of machine learning (ML), its ability to build models by leveraging real-world data is also a big limitation; the quality and quantity of training data bound the validity domain of ML models. On the other hand, expert models are designed from first principles or experiences and labelled scientific if validated on curated real-world data, often even harvested for this specific purpose, as advised by the scientific method since Galileo. Expert models only describe idealized versions of the world which may hinder their deployment for important tasks such as accurate forecasting or parameter inference. This workshop focuses on the combination of two modelling paradigms: scientific and ML modelling. Sometimes called hybrid learning or grey-box modelling, this combination should 1) unlock new applications for expert models, and 2) leverage the data compressed within scientific models to improve the quality of modern ML models. In this spirit, the workshop focuses on the symbiosis between these two complementary modelling approaches; it aims to be a “rendezvous” between the involved communities, spanning sub-fields of science, engineering and health, and encompassing ML, to allow them to present their respective problems and solutions and foster new collaborations. The workshop invites researchers to contribute to such topics; see Call for Papers and Call for Scientific Models for more details.

Gradients and derivatives are integral to machine learning, as they enable gradient-based optimization. In many real applications, however, models rest on algorithmic components that implement discrete decisions, or rely on discrete intermediate representations and structures. These discrete steps are intrinsically non-differentiable and accordingly break the flow of gradients. To use gradient-based approaches to learn the parameters of such models requires turning these non-differentiable components differentiable. This can be done with careful considerations, notably, using smoothing or relaxations to propose differentiable proxies for these components. With the advent of modular deep learning frameworks, these ideas have become more popular than ever in many fields of machine learning, generating in a short time-span a multitude of "differentiable everything", impacting topics as varied as rendering, sorting and ranking, convex optimizers, shortest-paths, dynamic programming, physics simulations, NN architecture search, top-k, graph algorithms, weakly- and self-supervised learning, and many more.

As machine learning-based systems are increasingly deployed in safety-critical applications, providing formal guarantees on their trustworthiness becomes ever more important. To facilitate the investigation of this challenging problem, we propose the 2nd Workshop on Formal Verification of Machine Learning (WFVML). WFVML will raise awareness for the importance of the formal verification of machine learning systems, bring together researchers from diverse backgrounds with interest in the topic, and enable the discussion of open problems as well as promising avenues in this emerging research area. Building on the success of last year, WFVML features a diverse panel of 8 confirmed invited speakers who made foundational contributions to the young field and an experienced and diverse multi-institutional organizing team of 10, including pioneering proponents of machine learning verification. A schedule combining invited talks, contributed talks, poster sessions, and a panel will provide opportunities and input for open discussions, with remote participation enabled via Zoom. Please see our website ml-verification.com for more details.

Generative modeling has recently gained massive attention given high-profile successes in natural language processing and computer vision. However, there remain major challenges in deploying generative models for real-world impact in domains like healthcare and biology. This is a challenging agenda that requires collaboration across multiple research fields and industry stakeholders. This workshop aims to advance such interdisciplinary conversations around challenges in deploying generative models – the lessons learned by deploying large language models could be impactful for high stakes domains like medicine and biology. Specifically, we will solicit contributions that prioritize (1) Multimodal capabilities in generative modeling, (2) Deployment-critical features in generative models such as Safety, Interpretability, Robustness, Ethics, Fairness and Privacy, and (3) Human facing evaluation of generative models. The topic of generative modeling is extremely relevant to the core audience of ICML. Modern generative models impact several fields outside machine learning and hence responsible deployment of such powerful algorithms has become a major concern of researchers in academia and industry alike. ICML, being the flagship conference of Machine learning, is the perfect place to facilitate this cross disciplinary sharing of knowledge.

Recent advances in algorithmic design and principled, theory-driven deep learning architectures have sparked a growing interest in control and dynamical system theory. Complementary, machine learning plays an important role in enhancing existing control theory algorithms in terms of performance and scalability. The boundaries between both disciplines are blurring even further with the rise of modern reinforcement learning, a field at the crossroad of data-driven control theory and machine learning. This workshop aims to unravel the mutual relationship between learning, control, and dynamical systems and to shed light on recent parallel developments in different communities. Strengthening the connection between learning and control will open new possibilities for interdisciplinary research areas.

Modern applications of machine learning seek to extract insights from high-dimensional datasets. The goal of the High-dimensional Learning Dynamics (HiLD) Workshop is to predict and analyze the dynamics of learning algorithms when the number of samples and parameters are large. This workshop seeks to spur research and collaboration around:

1. Developing analyzable models and dynamics to explain observed deep neural network phenomena;
2. Creating mathematical frameworks for scaling limits of neural network dynamics as width and depth grow, which often defy low-dimensional geometric intuitions;
3. The role of overparameterization and how this leads to conserved quantities in the dynamics and the emergence of geometric invariants, with links to Noether's theorem, etc;
4. Provable impacts of the choice of optimization algorithm, hyper-parameters, and neural network architectures on training/test dynamics.

HiLD Workshop aims to bring together experts from classical random matrix theory, optimization, high-dimensional statistics/probability, and statistical physics to share their perspectives while leveraging crossover experts in ML. It seeks to create synergies between these two groups which often do not interact. Through a series of talks, poster sessions, and panel discussions, the workshop will tackle questions on dynamics of learning algorithms at the interface of random matrix theory, high-dimensional statistics, SDEs, and ML.

Thinking fast and automatic vs. slow and deliberate (respectively System I and II) is a popular analogy when comparing data-driven learning to the good old-fashion symbolic reasoning approaches. Underlying this analogy lies the different capabilities of both systems, or lack thereof. While data-driven learning (System I) has striking performance advantages over symbolic reasoning (System II), it lacks abilities such as abstraction, comprehensibility and contextual awareness. Symbolic reasoning, on the other hand, tackles those issues but tends to lag behind data-driven learning when it comes to speedy, efficient and automated decision-making. In the current state of matters to combat issues on both sides, there is an increasing consensus among the machine learning and artificial intelligence communities to draw out the best of both worlds and unify data-driven approaches with rule-based, symbolic, logical and commonsense reasoning. This workshop aims to discuss emerging advances and challenges on this topic, in particular at the intersection of data-driven paradigms and knowledge and logical reasoning. We focus on both directions of this intersection:
Knowledge and Logical Reasoning for Data-driven Learning: In this direction, we will investigate the role of rule-based, knowledge and logical reasoning to enable more deliberate and trustworthy data-driven learning.
Data-driven Learning for Knowledge and Logical Reasoning: In this reverse direction, we will explore the capabilities of data-driven approaches to derive knowledge, logical and commonsense reasoning from data.

Learning from human preferences or preference-based learning has been critical to major advancements in AI and machine learning. Since human beings are naturally more reliable at providing feedback on a relative scale compared to numerical values, collecting preference feedback is more budget-friendly and involves less bias. The broad objective of this workshop is twofold:1) Bring together different communities where preference-based learning has played a major role. This includes dueling bandits, multi-agent games, econometrics, social choice theory, reinforcement learning, optimization, robotics and many more, for which we aim to create a suitable forum to exchange techniques, ideas, learn from each other and potentially create new and innovative research questions. 2) Connect theory to practice by identifying real-world systems which can benefit from incorporating preference feedback, such as marketing, revenue management, search engine optimization, recommender systems, healthcare, language modeling, interactive chatbots, text summarization, robotics, and so on.We will consider our workshop a success if it inspires researchers to embark on novel insights in the general area of preference-based learning: Bringing attention from different communities to foster dissemination, cross-fertilization and discussion at scale. Especially, building bridges between experimental researchers and theorists towards developing better models and practical algorithms, and encouraging participants to propose, sketch, and discuss new starting points, questions or applications.

The workshop focuses on theory, methodology, and application of structured probabilistic inference and generative modeling, both of which are important topics in machine learning.Specifically, probabilistic inference addresses the problem of amortization,sampling, and integration of complex quantities from graphical models, while generative modeling captures the underlying probability distributions of a dataset. Apart from applications in computer vision, natural language processing, and speech recognition, probabilistic inference and generative modeling approaches have also been widely used in natural science domains, including physics, chemistry, molecular biology, and medicine. Despite the promising results, probabilistic methods face challenges when applied to highly structured data, which are ubiquitous in real-world settings, limiting the applications of such methods. This workshop aims to bring experts from diverse backgrounds and related domains together to discuss the applications and challenges of probabilistic methods. The workshop will emphasize challenges in encoding domain knowledge when learning representations, performing inference and generations. By bringing together experts from academia and industry, the workshop will provide a platform for researchers to share their latest results and ideas, fostering collaboration and discussion in the field of probabilistic methods.

Much of the data that is fueling current rapid advances in machine learning is high dimensional, structurally complex, and strongly nonlinear. This poses challenges for researcher intuition when they ask (i) how and why current algorithms work and (ii) what tools will lead to the next big break-though. Mathematicians working in topology, algebra, and geometry have more than a hundred years worth of finely-developed machinery whose purpose is to give structure to, help build intuition about, and generally better understand spaces and structures beyond those that we can naturally understand. Following on the success of the first TAG-ML workshop in 2022, this workshop will showcase work which brings methods from topology, algebra, and geometry and uses them to help answer challenging questions in machine learning. Topics include mathematical machine learning, explainability, training schemes, novel algorithms, performance metrics, and performance guarantees. All accepted papers will be included in an associated PMLR volume.

Interactive learning encompasses online learning, continual learning, active learning, bandits, reinforcement learning, and other settings where an algorithm must learn while interacting with a continual stream of data. Such problems often involve exploration-exploitation dilemmas, which can be elegantly handled with probabilistic and Bayesian methods. Deep interactive learning methods leveraging neural networks are typically used when the setting involves rich observations, such as images. As a result, both probabilistic and deep interactive learning methods are growing in popularity. However, acquiring observations in an interactive fashion with the environment can be costly. There is therefore great interest in understanding when sample-efficient learning with probabilistic and deep interactive learning can be expected or guaranteed. Within statistical learning theory, PAC-Bayesian theory is designed for the analysis of probabilistic learning methods. It has recently been shown to be well-suited for the analysis of deep learning methods. This workshop aims to bring together researchers from the broad Bayesian and interactive learning communities in order to foster the emergence of new ideas that could contribute to both theoretical and empirical advancement of PAC-Bayesian theory in interactive learning settings.

Proposed around 2016 as privacy preserving techniques, federated learning and analytics (FL & FA) made remarkable progress in theory and practice in recent years. However, there is a growing disconnect between theoretical research and practical applications of federated learning. This workshop aims to bring academics and practitioners closer together to exchange ideas: discuss actual systems and practical applications to inspire researchers to work on theoretical and practical research questions that lead to real-world impact; understand the current development and highlight future directions. To achieve this goal, we aim to have a set of keynote talks and panelists by industry researchers focused on deploying federated learning and analytics in practice, and academic research leaders who are interested in bridging the gap between the theory and practice.

For more details, please visit the workshop webpage at https://fl-icml2023.github.io

Main session: 316C

Breakout Rooms: 326A and 326B

The Women in Machine Learning (WiML) workshop was founded in 2006 to forge connections within the relatively small community of women working in machine learning, to encourage mentorship, exchange of ideas, and promote communication. The workshop attracts representatives from academia and industry whose contributed talks showcase some of the cutting-edge research done by women. In addition to technical presentations and discussions, the workshop aims to incite debate on promising research avenues and career choices for machine learning professionals. This year we are planning to hold an in-person un-workshop co-located with ICML 2023. The un-workshop included several time slots of small group discussions happening in parallel, which fosters a free-format discussion on pre-selected topics primarily driven by participants.

Applying machine learning (ML) in healthcare is gaining momentum rapidly. However, the black-box characteristics of the existing ML approach inevitably lead to less interpretability and verifiability in making clinical predictions. To enhance the interpretability of medical intelligence, it becomes critical to develop methodologies to explain predictions as these systems are pervasively being introduced to the healthcare domain, which requires a higher level of safety and security. Such methodologies would make medical decisions more trustworthy and reliable for physicians, which could ultimately facilitate the deployment. In addition, it is essential to develop more interpretable and transparent ML systems. For instance, by exploiting structured knowledge or prior clinical information, one can design models to learn aspects more aligned with clinical reasoning. Also, it may help mitigate biases in the learning process, or identify more relevant variables for making medical decisions.In this workshop, we aim to bring together researchers in ML, computer vision, healthcare, medicine, NLP, public health, computational biology, biomedical informatics, and clinical fields to facilitate discussions including related challenges, definition, formalisms, and evaluation protocols regarding interpretable medical machine intelligence. Our workshop will be in a large-attendance talk format. The expected number of attendees is about 150. The workshop appeals to ICML audiences as interpretability is a major challenge to deploy ML in critical domains such as healthcare. By providing a platform that fosters potential collaborations and discussions between attendees, we hope the workshop is fruitful in offering a step toward building autonomous clinical decision systems with a higher-level understanding of interpretability.