Aditya Grover (Stanford University)
Aditya Grover is a final year PhD student at Stanford University (expected graduation Sept 2020). His research focuses on probabilistic modeling for representation learning and reasoning in high dimensions, and is grounded in applications in science and sustainability, such as weather forecasting and electric batteries. Aditya’s research has been published in top machine learning and scientific venues including Nature, covered by various media outlets, included in widely-used open source software, and deployed into production at major technology companies. He has won several awards for his work, including a best paper award (StarAI), a best undergraduate thesis award, a Stanford Centennial Teaching Award, a Stanford Data Science Scholarship, a Lieberman Fellowship, and a Microsoft Research Ph.D. Fellowship. Aditya received his masters from Stanford University and bachelors from IIT Delhi, both in computer science.
Deep Generative Models and Applications to Scientific Discovery
Abstract: Generative models are a key paradigm for probabilistic reasoning within graphical models and probabilistic programming languages. Recent advancements in parameterizing these models using neural networks and stochastic optimization using gradient-based techniques have enabled scalable modeling of high-dimensional data across a breadth of modalities and applications.
The first half of this tutorial will provide a holistic review of the major families of deep generative models, including generative adversarial networks, variational autoencoders, normalizing flows, and autoregressive models. For each of these models, we will discuss the probabilistic formulations, learning algorithms, and relationships with other models. The second half of the tutorial will demonstrate approaches for using deep generative models for scientific discovery, such as materials and drug discovery, compressed sensing, and more. Finally, we will conclude with a discussion of the current challenges in the field and promising avenues for future research.