Invited Speakers

AI is changing the financial industry, and indeed, the world, at an ever accelerating pace. The current generation of AI models is different from the previous state of the art in important ways. Large transformer models are broadly capable - exhibiting state-of-the-art, and even human-level performance, on many tasks without problem-specific training - and uniquely accessible, allowing non-experts to interact with them using natural language. Nonetheless, they also have important limitations. In this talk, we will explore the current state of the art in financial AI applications, discuss the challenges of AI adoption in the enterprise, and talk about the risks and future directions of AI development. We will then look at our recent paper (https://arxiv.org/abs/2409.10470) about non-convex online bilevel optimization, and discuss applications of the new method to financial time series analysis and hyperparameter optimization.
The talk will conclude with a Q&A session.

About the Speaker

Gary is the Head of Quant Technology Strategy in the Office of the CTO at Bloomberg. Prior to taking on this role, he created and headed the company’s Machine Learning Engineering group, leading projects at the intersection of computational linguistics, machine learning and finance, such as sentiment analysis of financial news, market impact indicators, statistical text classification, social media analytics, question answering, and predictive modeling of financial markets.
Prior to joining Bloomberg in 2007, Gary had earned degrees with distinction in physics, mathematics, and computer science from Boston University.
He is engaged in advisory roles with FinTech and Machine Learning startups and has worked at a variety of technology and academic organizations over the last 20 years. In addition to speaking regularly at industry and academic events around the globe, he is a member of the KDD Data Science + Journalism workshop program committee and the advisory board for the AI & Data Science in Trading conference series. He is also an adjunct professor at Columbia University, and a co-organizer of the annual Machine Learning in Finance conference at Columbia University.

Despite great successes, current deep learning methods cannot learn effectively during normal operation, which makes them ill-suited for reinforcement learning or, really, for any general intelligence. In particular, conventional artificial neural networks fail catastrophically in classic supervised learning testbeds, such as ImageNet, when those testbeds are extended to require ongoing learning. In this talk, I argue that this failure is not inherent in neural networks, but just of the algorithms currently used. For example, a simple modification of the standard backpropagation algorithm, known as continual backpropagation, greatly improves performance in continual learning settings. Such results suggest exploring network learning algorithms explicitly designed for continual and reversible change, such as Dynamic deep learning networks, which continually adapt at multiple levels including 1) their weights, 2) their step-size parameters, and 3) their interconnection structure.

About the Speaker

Rich Sutton is research scientist at Keen Technologies, professor in the Department of Computing Science at the University of Alberta, chief scientific advisor of the Alberta Machine Intelligence Institute (Amii), and fellow of the Royal Society of London, the Royal Society of Canada, the Association for the Advancement of Artificial Intelligence, Amii, and CIFAR. He received a PhD in computer science from the University of Massachusetts in 1984 and a BA in psychology from Stanford University in 1978. Prior to joining the University of Alberta in 2003, he worked in industry at AT&T Labs and GTE Labs, and in academia at the University of Massachusetts. He helped found DeepMind Alberta in 2017 and worked there until its dissolution in 2023. At the University of Alberta, Sutton founded the Reinforcement Learning and Artificial Intelligence Lab, which now consists of ten principal investigators and about 100 people altogether. Sutton is co-author of the textbook Reinforcement Learning: An Introduction, and his scientific publications have been cited more than 140,000 times. He is also a libertarian, a chess player, and a cancer survivor.

The impressive developments in language and image models have both opened new creative possibilities for artists and surfaced ethical concerns about the impact of generative AI upon the arts. In this talk, I will cover the subject of AI as a creativity support tool, focusing on theatre and live performance with generative AI. I will illustrate the talk with an example of my theater company, Improbotics, that has used AI for improvised comedy since 2016 and has recently engaged the wider public at Edinburgh Festival Fringe. I will also cover socio-technical research at Google DeepMind on participatory AI with artists, including the evaluation of generative AI tools for visual artists or for co-writing screenplays, theatre plays and comedy.

About the Speaker

Dr Piotr Mirowski is a Staff Research Scientist at Google DeepMind, a Visiting Researcher and Knowledge Exchange Scholar at Goldsmiths, University of London, and the co-founder and Director of Improbotics. His research on artificial intelligence covers the subjects of reinforcement learning, navigation, weather and climate forecasting, as well as a socio-technical systems approach to human-machine collaboration and to computational creativity. He is the author of over 75 papers that have been published in prestigious journals including Nature. Piotr studied computer science in France at ENSEEIHT Toulouse and obtained his PhD in computer science in 2011 at New York University, with a thesis supervised by Prof. Yann LeCun (Outstanding Dissertation Award, 2011). A trained actor himself (London School of Dramatic Art), Piotr created Improbotics, a theatre company where human actors and robots improvise live comedy performances and investigate the use of AI for artistic human and machine-based co-creation, aiming at bridging the arts and sciences.

Combinatorial Optimization is crucial to numerous real-world applications, yet still presents challenges due to its (NP-)hard nature. Amongst existing approaches, heuristics often offer the best trade-off between quality and scalability, making them suitable for industrial use. While Reinforcement Learning (RL) offers a flexible framework for designing heuristics, its adoption over handcrafted heuristics remains incomplete within industrial solvers. Existing learned methods still lack the ability to adapt to specific instances, failing to fully utilise newly available information within the constraints of the budget. In response, we present MEMENTO, an RL approach that leverages memory to improve the adaptation of neural solvers at inference time.

About the Speaker

Felix Chalumeau is a Research Engineer at InstaDeep, where he works on reinforcement learning for combinatorial optimisation, with a focus on diversity and population-based approaches. He has also worked on other diversity-related topics, including neuroevolution, quality diversity, skill discovery and collaborative skills for multi-agent learning, with publications in international ML conferences, including Neurips and ICLR. Prior to InstaDeep, he studied at Imperial College London and Ecole polytechnique.

Despite all their recent advances, current AI methods are still brittle and fail when confronted with unexpected situations. Biological intelligent systems, on the other hand, can rapidly adapt and display an inherent level of resilience. While being inspired by the brain, the current artificial neural network paradigm abstracted away many of the properties that could turn out essential in our goal to create a more general artificial intelligence. In this talk, I'll present some of our work in exploring alternative neural building blocks. For example, it is possible to allow completely random networks to adapt to morphological damage in a robot in only a few trials through meta-learned local plasticity rules. Likewise, evolving different acitvation functions in random neural networks alone, enables them to master different reinforcement learning tasks, challenging our understanding of which ingredients to include in our neural networks. Finally, I will present our current work on Neural Developmental Program approach, in which we learn to grow artificial neural networks through a developmental process that mirrors key properties of embryonic development in biological organisms. The talk concludes with future research opportunities and challenges that we need to address to best capitalize on the same ideas that allowed biological intelligence to strive.

About the Speaker

Sebastian Risi is a Full Professor at the IT University of Copenhagen where he directs the Creative AI Lab, and co-directs the Robotics, Evolution and Art Lab (REAL).  Before joining ITU, he did a postdoc at Cornell University and before that, he obtained a Ph.D. from the University of Central Florida. As one of the pioneers in the emerging field of collective intelligence for deep learning, he investigates how we can make current AI approaches more robust and adaptive. He has won several international scientific awards, including multiple best paper awards, an ERC Consolidator Grant in 2022, the Distinguished Young Investigator in Artificial Life 2018 award, a Google Faculty Research Award in 2019, and an Amazon Research Award in 2020. His interdisciplinary work has been published in major machine learning, artificial life, and human-computer interaction conferences, including AAAI, NeurIPS, ICLR, Nature Machine Intelligence, ALIFE, GECCO, and CHI.

We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

About the Speaker

Jake has a background in deep learning for robot navigation from Queensland University of Technology in Brisbane, Australia. He has been working on reinforcement learning and large-scale deep learning at Google DeepMind since 2018, and has been involved in projects on imitation learning in NetHack, generalist agents via Gato, and most recently generative world models in Genie.

We investigate how multi-agent learning can enable safe deployment and evaluation of autonomous systems operating in safety-critical, mixed human-robot settings. Using a case study of a 100-vehicle, real-world deployment of RL-based traffic-smoothing autonomous vehicles (AVs), we discuss the challenges of estimating when a controller will successfully bridge the sim-to-real gap. We then discuss our work on building human-like, capable simulated agents using regularized self-play techniques. Finally, we discuss some of the challenges of MARL at scale and the new simulators we are designing to address them.

About the Speaker

Eugene Vinitsky is an assistant professor in Transportation Engineering  at NYU, a member of the C2SMARTER consortium on congestion reduction,  and a part-time research scientist at Apple. He works primarily on  multi-agent learning with a focus on its potential use in transportation  systems and robotics. At UC Berkeley, where he was advised by Alexandre Bayen, he received his PhD in controls engineering and received an MS and BS in physics from UC Santa Barbara and Caltech respectively. During his PhD he spent time at DeepMind, Tesla Autopilot, and FAIR.

Attention-based models have been a key element of many recent breakthroughs in deep learning. Two key components of Attention are the structure of its input (which consists of keys, values and queries) and the computations by which these three are combined. In this paper we explore the space of models that share said input structure but are not restricted to the computations of Attention. We refer to this space as Keys-Values-Queries (KVQ) Space. Our goal is to determine whether there are any other stackable models in KVQ Space that Attention cannot efficiently approximate, which we can implement with our current deep learning toolbox and that solve problems that are interesting to the community. Maybe surprisingly, the solution to the standard least squares problem satisfies these properties. A neural network module that is able to compute this solution not only enriches the set of computations that a neural network can represent but is also provably a strict generalisation of Linear Attention. Even more surprisingly the computational complexity of this module is exactly the same as that of Attention, making it a suitable drop in replacement. With this novel connection between classical machine learning (least squares) and modern deep learning (Attention) established we justify a variation of our model which generalises regular Attention in the same way. Both new modules are put to the test an a wide spectrum of tasks ranging from few-shot learning to policy distillation that confirm their real-worlds applicability.

About the Speaker

Marta is a senior research scientist at DeepMind where she has primarily worked on deep generative models and meta learning. As part of this research she has been involved in developing Generative Query Networks and led the work on Neural Processes. In addition to generative models her recent interests have expanded to multi-agent systems and game theory. Prior to DeepMind Marta obtained her PhD from Imperial College London.

First-person view (FPV) drone racing is a televised sport in which professional competitors pilot high-speed quadcopters through a 3D circuit. The pilots see the environment from the perspective of their drone by means of an onboard camera video-stream. In this talk I will explain Swift, an autonomous system that can race quadcopters at the level of the human world champions. The system combines deep reinforcement learning (RL) in simulation with data collected in the physical world. Our Swift drone competed against three human champions, including the world champions of two international leagues, in real-world head-to-head races and won several races against each of the human champions. The autonomous drone demonstrated the fastest recorded race time.

About the Speaker

Leonard Bauersfeld did his Masters at ETH Zurich  in "Robotics, Systems, and Control" where he graduated with distinction in 2021. Currently he is a PhD Student in Robotics at the University of Zurich working in the "Robotics and Perception Group" under the lead of roboticist Davide Scaramuzza.  He works on drone modeling, agile vision-based flight and novel machine learning approaches to push the frontiers of autonomous UAV navigation. He was part of the team that impressively beat the world champions of drone racing in a fair head-to-head race with an autonomous drone. Besides working on drones, he is a photographer and enjoys taking pictures of nature as well as far-away astronomical objects, such as nebulas and galaxies.

Developing agents capable of modeling complex environments and human behaviors within them is a key goal of artificial intelligence research. Progress towards this goal has exciting potential for applications in video games, from new tools that empower game developers to realize new creative visions, to enabling new kinds of immersive player experiences. This talk focuses on recent advances of my team at Microsoft Research towards scalable machine learning architectures that effectively capture human gameplay data.

In the first part of my talk, I will focus on diffusion models as generative models of human behavior. Previously shown to have impressive image generation capabilities, I present insights that unlock applications to imitation learning for sequential decision making [1]. In the second part of my talk, I discuss a recent project taking ideas from language modeling to build a generative sequence model of an Xbox game [2].

[1] Imitating human behaviour with diffusion models, Pearce et al., ICLR 2023, https://aka.ms/bc-diffusion

[2] Tales of Scaling Up Generative AI for Video Games, MSR Cambridge Game Intelligence team, under submission.

About the Speaker

Katja Hofmann is a Senior Principal Researcher at Microsoft Research. She leads a team that focuses on modern machine learning and reinforcement learning for Games, with the mission to advance the state of the art in sequential decision making, driven by current and future applications in video games. She and her team share the belief that games will drive a transformation of how people interact with AI technology. Her long-term goal is to develop systems that learn to collaborate with people, to empower their users and help solve complex real-world problems.

Whether in biological design, causal discovery, material production, or physical sciences, one often faces decisions regarding which new data to collect or experiments to perform. There is thus a pressing need for adaptive algorithms that make confident decisions about data collection processes and enable efficient and robust learning. In this talk, I will delve into the fundamental questions related to these requirements. How can we quantify uncertainty and efficiently learn to discover robust solutions? How can we design learning-based decision-making methods that are resistant to outliers, data shifts, and attacks? How can we utilize the inherent problem structure to achieve efficient learning? In light of the previous questions, I will examine the core statistical and robustness aspects through the perspective of Bayesian optimization and reinforcement learning. I will highlight the shortcomings of standard methods and present novel algorithms that come with strong theoretical guarantees. I will also showcase their robust performance in various applications by utilizing real-world data and popular benchmarks and finally map the main avenues for future research.  

About the Speaker

Ilija Bogunovic is a Lecturer (assistant professor) in the Electrical Engineering Department at the University College London. Before that, he was a postdoctoral researcher in the Machine Learning Institute and Learning and Adaptive Systems group at ETH Zurich. He received a Ph.D. in Computer and Communication Sciences from EPFL and an MSc in Computer Science from ETH Zurich. His work has been recognized through a Google Research Scholar Program Award and EPSRC New Investigator Award.

His research interests are centered around data-efficient interactive machine learning, reinforcement learning, reliability and robustness considerations in data-driven algorithms and are motivated by a range of emerging real-world applications. He co-founded a recurring ReALML ICML workshop on “Adaptive Experimental Design and Active Learning in the Real World".

In this talk I will focus on State Space Models (SSM), a recently introduced family of sequential models and specifically discuss the relationship between SSMs and recurrent neural networks. I will start with a short history of architecture design for language modelling, which I will use as a motivating task. This will allow me to provide some insights in the evolution of RNN architectures, and why some choices behind the SSM architecture seemed counter-intuitive. Most of the talk will focus on introducing the Linear Recurrent Unit architecture, explaining the role of the various modifications from traditional non-linear recurrent models. 

The talk will conclude with some open questions about the role recurrent architectures could or should play, and potentially the less well understood relationship between these SSM models and transformer like architectures. 

About the Speaker

Razvan Pascanu has been a research scientist at Google DeepMind since 2014. Before this, he did his PhD in Montréal with prof. Yoshua Bengio, working on understanding deep networks, recurrent models and optimization. Since he joined DeepMind he has also had significant contributions in deep reinforcement learning, continual learning, meta-learning, graph neural networks as well as continuing his research agenda of understanding deep learning, recurrent models and optimization. Please see his scholar page for specific contributions. He is also actively promoting AI research and education as a main organizer of Conference on Life-long Learning Agents (CoLLAs) lifelong-ml.cc , Eastern European Machine Learning Summer School (EEML) www.eeml.eu and www.workshops.eeml.eu as well as different workshops at NeurIPS, ICML and ICLR.

One of the key features of intelligent beings is the capacity to explore and discovery an unknown environment and to progressively learn how to control it. This process is not driven by an explicit reward and it may unfold in a completely unsupervised way. In this talk I will propose a formalization of unsupervised discovery and exploration as the process of incrementally learning policies that reach goals of increasing difficulty. The resulting goal-based policy then allows the agent to solve any goal-reaching task at downstream time with no additional learning or planning. I will illustrate algorithmic principles, theoretical guarantees, and preliminary empirical results that could lay the foundations for designing agents that can efficiently learn in open-ended environments.

References:

On unsupervised exploration:

Adaptive Multi-Goal Exploration; AISTATS 2022

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching; ICLR 2022

A Provably Efficient Sample Collection Strategy for Reinforcement Learning; NeurIPS 2021

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs; NeurIPS 2020

On exploration for goal-based RL:

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret; NeurIPS 2021

Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model; A 

About the Speaker

Alessandro is a research scientist at Meta AI (/FAIR), where he has been since 2017. Prior to working at Meta, he completed a PhD at Politecnico di Milano and worked as a researcher at INRIA Lille. His main research topic is reinforcement learning, with extensive contributions on both the theoretical and algorithmic aspects of RL. In the last ten years he has studied the exploration-exploitation dilemma both in the multi-armed bandit and reinforcement learning framework, notably on the problems of regret minimization, best-arm identification, pure exploration, and hierarchical RL.

Improving the efficiency of algorithms for fundamental computational tasks such as matrix multiplication can have widespread impact, as it affects the overall speed of a large amount of computations. The automatic discovery of algorithms using machine learning offers the prospect of reaching beyond human intuition and outperforming the current best human-designed algorithms. In this talk I'll present AlphaTensor, our reinforcement learning agent based on AlphaZero for discovering efficient and provably correct algorithms for the multiplication of arbitrary matrices. AlphaTensor discovered algorithms that outperform the state-of-the-art complexity for many matrix sizes. Particularly relevant is the case of 4 × 4 matrices in a finite field, where AlphaTensor's algorithm improves on Strassen's two-level algorithm for the first time since its discovery 50 years ago. I'll present our problem formulation as a single-player game, the key ingredients that enable tackling such difficult mathematical problems using reinforcement learning, and the flexibility of the AlphaTensor framework. 

About the Speaker

Alhussein Fawzi is a Research Scientist in the Science team at DeepMind, where he leads the algorithmic discovery efforts. He is broadly interested in using machine learning to unlock new scientific discoveries. He obtained his PhD in machine learning and computer vision from EPFL in 2016.

Reward is the driving force for reinforcement-learning agents. In this talk, I will present our recent NeurIPS paper that explores the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of “task” that might be of interest: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories. Our main results prove that while Markov reward can express many of these tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists. I conclude by summarizing recent follow up work that studies alternatives for enriching the expressivity of reward. 

About the Speaker

David Abel is a Research Scientist at DeepMind in London. Before that, he completed his Ph.D in computer science and Masters in philosophy at Brown University, advised by Michael Littman (CS) and Josh Schechter (philosophy). 

In the past few years, deep reinforcement learning (RL) has led to impressive achievements in games and robotics. However, current state-of-the-art RL methods struggle to generalize to scenarios they haven’t experienced during training. In this talk, I will show how we can leverage diverse data and a minimal set of inductive biases to generalize to new task instances. First, I will discuss how we can use data augmentation to learn policies which are invariant to task-irrelevant changes in the observations. Then, I will show how we can generalize to new task instances with unseen states and layouts by decoupling the representation of the policy and value function. And finally, I will briefly describe how we can quickly adapt to new dynamics by learning a value function for a family of behaviors and environments.

About the Speaker

Roberta is a research scientist at Meta AI / FAIR. Previously, she did her PhD in computer science at NYU, advised by Rob Fergus. Her research focuses on designing machine learning algorithms that can make robust sequential decisions in complex environments. In particular, Roberta works in the area of deep reinforcement learning, with a focus on generalization, adaptation, continual, and open-ended learning. During her PhD, she spent time as an intern at DeepMind, Microsoft Research, and Facebook AI Research. Roberta also holds a B.A. in Astrophysics from Princeton University, where she worked on theoretical cosmology and supernovae simulations.