Self-predictive learning (aka non-contrastive learning) has become an increasingly important paradigm for representation learning. Self-predictive learning is simple yet effective: it learns without contrastive examples yet extracts useful representations through a self-predicitve objective. A common myth with self-predictive learning is that the optimization objective itself yields trivial representations as globally optimal solutions, yet practical implementations can produce meaningful solutions. 

We reconcile the theory-practice gap by studying the learning dynamics of self-predictive learning. Our analysis is based on analyzing a non-linear ODE system that sheds light on why despite a seemingly problematic optimization objective, self-predictive learning does not collapse, which echoes with important implementation "tricks" in practice. Our results also show that in a linear setup, self-predictive learning can be understood as gradient based PCA or SVD on the data matrix, hinting at meaningful representations to be captured through the learning process.

This talk is based on our ICML 2023 paper "Understanding self-predictive learning for reinforcement learning".

Electron cryomicroscopy (cryo-EM) is an imaging technique widely used in structural biology to determine the three-dimensional structure of biological molecules from noisy two-dimensional projections with unknown orientations. As the typical pipeline involves processing large amounts of data, efficient algorithms are crucial for fast and reliable results. The stochastic gradient descent (SGD) algorithm has been used to improve the speed of ab initio reconstruction, which results in a first, low-resolution estimation of the volume representing the molecule of interest, but has yet to be applied successfully in the high-resolution regime, where expectation-maximization algorithms achieve state-of-the-art results, at a high computational cost. 
In this work, we investigate the conditioning of the optimisation problem and show that the large condition number prevents the successful application of gradient descent-based methods at high resolution. 
Our results include a theoretical analysis of the condition number of the optimisation problem in a simplified setting where the individual projection directions are known, an algorithm based on computing a diagonal preconditioner using Hutchinson's diagonal estimator, and numerical experiments showing the improvement in the convergence speed when using the estimated preconditioner with SGD. The preconditioned SGD approach can potentially enable a simple and unified approach to ab initio reconstruction and high-resolution refinement with faster convergence speed and higher flexibility, and our results are a promising step in this direction.

Since Gromov's celebrated polynomial growth theorem, the understanding of nilpotent groups has become a cornerstone of geometric group theory. An interesting aspect is the conjectural quasiisometry classification of nilpotent groups. One important quasiisometry invariant that plays a significant role in the pursuit of classifying these groups is the Dehn function, which quantifies the solvability of the world problem of a finitely presented group. Notably, Gersten, Holt, and Riley's work established that the Dehn function of a nilpotent group of class $c$ is bounded above by $n^{c+1}$.  

In this talk, I will explain recent results that allow us to compute Dehn functions for extensive families of nilpotent groups arising as central products. Consequently, we obtain a large collection of pairs of nilpotent groups with bilipschitz equivalent asymptotic cones but with different Dehn functions.

This talk is based on joint work with Claudio Llosa Isenrich and Gabriel Pallier.

Since Gromov's celebrated polynomial growth theorem, the understanding of nilpotent groups has become a cornerstone of geometric group theory. An interesting aspect is the conjectural quasiisometry classification of nilpotent groups. One important quasiisometry invariant that plays a significant role in the pursuit of classifying these groups is the Dehn function, which quantifies the solvability of the world problem of a finitely presented group. Notably, Gersten, Holt, and Riley's work established that the Dehn function of a nilpotent group of class $c$ is bounded above by $n^{c+1}$.  

In this talk, I will explain recent results that allow us to compute Dehn functions for extensive families of nilpotent groups arising as central products. Consequently, we obtain a large collection of pairs of nilpotent groups with bilipschitz equivalent asymptotic cones but with different Dehn functions.

This talk is based on joint work with Claudio Llosa Isenrich and Gabriel Pallier.

We define a version of algebraic K-theory for bornological algebras, using the recently developed continuous K-theory by Efimov. In the commutative setting, we prove that this invariant satisfies descent for various topologies that arise in analytic geometry, generalising the results of Thomason-Trobaugh for schemes. Finally, we prove a version of the Grothendieck-Riemann-Roch Theorem for analytic spaces. Joint work with Jack Kelly and Federico Bambozzi. 

Let G be a reductive group over a finite field F of characteristic p. I will present work with Tzu-Jan Li in which we determine the endomorphism algebra of the Gelfand-Graev representation of the finite group G(F) where the coefficients are taken to be l-adic integers, for l a good prime of G distinct from p. Our result can be viewed as a finite-field analogue of the local Langlands correspondence in families. 

The "curse of dimensionality" refers to the host of difficulties that occur when we attempt to extend our intuition about what happens in low dimensions (i.e. when there are only a few features or variables)  to very high dimensions (when there are hundreds or thousands of features, such as in genomics or imaging).  With very high-dimensional data, there is often an intuition that although the data is nominally very high dimensional, it is typically concentrated around a much lower dimensional, although non-linear set. There are many approaches to identifying and representing these subsets.  We will discuss topological approaches, which represent non-linear sets with graphs and simplicial complexes, and permit the "measuring of the shape of the data" as a tool for identifying useful lower dimensional representations.