Previous Conferences & Workshops

Standard machine learning produces models that are highly accurate on average but that degrade dramatically when the test distribution deviates from the training distribution. While one can train robust models, this often comes at the expense of...

Let F be a CM field. Scholze constructed Galois representations associated to classes in the cohomology of locally symmetric spaces for GL_n/F with p-torsion coefficients. These Galois representations are expected to satisfy local-global...

Physical processes in the world often have a modular structure, with complexity emerging through combinations of simpler subsystems. Machine learning seeks to uncover and use regularities in the physical world. Although these regularities manifest...

Despite the success of deep learning, much of its success has existed in settings where the goal is to learn one, single-purpose function from data. However, in many contexts, we hope to optimize neural networks for multiple, distinct tasks (i.e...

In this talk, I will first introduce our recent work on the Deep Equilibrium Model (DEQ). Instead of stacking nonlinear layers, as is common in deep learning, this approach finds the equilibrium point of the repeated iteration of a single non-linear...

While the trend in machine learning has tended towards more complex hypothesis spaces, it is not clear that this extra complexity is always necessary or helpful for many domains. In particular, models and their predictions are often made easier to...

Through interactions with engineers and computer scientists over the years, including some current visitors at IAS, I have become pretty sold on the idea that machine learning is rich in questions which are interesting to pure mathematicians and...

Implicit generative models such as GANs have achieved remarkable progress at generating convincing fake images, but how well do they really match the distribution? Log-likelihood has been used extensively to evaluate generative models whenever it’s...

In this talk, I would like to share some of my reflections on the progress made in the field of interpretable machine learning. We will reflect on where we are going as a field, and what are the things that we need to be aware of to make progress...

Existing generative models are typically based on explicit representations of probability distributions (e.g., autoregressive or VAEs) or implicit sampling procedures (e.g., GANs). We propose an alternative approach based on modeling directly the...