Seminars Sorted by Series

In modern “Big Data” applications, structured learning is the most widely employed methodology. Within this paradigm, the fundamental challenge lies in developing practical, effective algorithmic inference methods. Often (e.g., deep learning)...

Deep learning builds upon the mysterious ability of gradient-based methods to solve related non-convex optimization problems. However, a complete theoretical understanding is missing even in the simpler setting of training a deep linear neural...

We consider adversarial online learning in a non-convex setting under the assumption that the learner has an access to an offline optimization oracle. In the most general unstructured setting of prediction with expert advice, Hazan and Koren (2016)...

Natural gradient descent holds the potential to speed up training of neural networks by correcting for the problem geometry and achieving desirable invariance properties. I’ll present Kronecker-Factored Approximate Curvature (K-FAC), a scalable...

Nonlinear Acceleration Algorithms, such as BFGS, were widely used in optimization due to their impressive performance even for large scale problems. However, these methods present a non negligeable number of drawbacks, such as a strong lack of...

We consider the problem of predicting the next observation given a sequence of past observations, and consider the extent to which accurate prediction requires complex algorithms that explicitly leverage long-range dependencies. Perhaps surprisingly...

Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la carte embedding, a simple and...

Understanding deep learning calls for addressing three fundamental questions: expressiveness, optimization and generalization. Expressiveness refers to the ability of compactly sized deep neural networks to represent functions capable of solving...

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure...

The current era of large scale machine learning powered by Deep Learning methods has brought about tremendous advances, driven by the lightweight Stochastic Gradient Descent (SGD) method. Despite relying on a simple algorithmic primitive, this era...

Suppose an agent is in an unknown Markov environment in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? One natural, intrinsically defined, objective problem is for the agent to learn a policy which...

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap...

The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative updates...

Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding algorithm...

Recent progress in optimization theory has shown how we may harness second-order, i.e. Hessian, information, for achieving faster rates for both convex and non-convex optimization problems. Given this observation, it is then natural to ask what sort...

Linear dynamical systems are a continuous subclass of reinforcement learning models that are widely used in robotics, finance, engineering, and meteorology. Classical control, since the works of Kalman, has focused on dynamics with Gaussian i.i.d...

In various applications, one is given the advice or predictions of several classifiers of unknown reliability, over multiple questions or queries. This scenario is different from standard supervised learning where classifier accuracy can be assessed...

Most people interact with machine learning systems on a daily basis. Such interactions often happen in strategic environments where people have incentives to manipulate the learning algorithms. As machine learning plays a more prominent role in our...

Modern machine learning often optimizes a nonconvex objective using simple algorithm such as gradient descent. One way of explaining the success of such simple algorithms is by analyzing the optimization landscape and show that all local minima are...

Linear regression in L_p-norm is a canonical optimization problem that arises in several applications, including sparse recovery, semi-supervised learning, and signal processing. Standard linear regression corresponds to p=2, and p=1 or infinity is...

This talk discusses three aspects of deep learning from a statistical perspective: interpolation, optimality and sparsity. The first one attempts to interpret the double descent phenomenon by precisely characterizing a U-shaped curve within the...

Minimax optimization, especially in its general nonconvex formulation, has found extensive applications in modern machine learning, in settings such as generative adversarial networks (GANs) and adversarial training. It brings a series of unique...

This talk focuses on a general phenomenon of "Frequency-Principle" that DNNs often fit target functions from low to high frequencies during the training. I will present empirical evidences on real datasets and deep networks of different settings as...

The classical regression problem seeks to estimate a function f on the basis of independent pairs $(x_i,y_i)$ where $\mathbb E[y_i]=f(x_i)$, $i=1,\dotsc,n$. In this talk, we consider statistical and computational aspects of the "uncoupled" version...

We make the case that over the coming decade, computer assisted reasoning will become far more widely used in the mathematical sciences. This includes interactive and automatic theorem verification, symbolic algebra, and emerging technologies such...

Online learning is a popular framework for sequential prediction problems. The standard approach to analyzing an algorithm's (learner's) performance in online learning is in terms of its empirical regret defined to be the excess loss suffered by the...

Function approximators, like deep neural networks, play a crucial role in building machine-learning based intelligent systems. This talk covers three core problems of function approximators: understanding function approximators, designing new...

Causal inference from observational data is a vital problem, but it comes with strong assumptions. Most methods require that we observe all confounders, variables that affect both the causal variables and the outcome variables. But whether we have...

I’ll discuss the Noisy Quadratic Model, the toy problem of minimizing a convex quadratic function with noisy gradient observations. While the NQM is simple enough to have closed-form dynamics for a variety of optimizers, it gives a surprising amount...

For a function K : R^d x R^d -> R, and a set P = {x_1, ..., x_n} in d-dimension, the K graph G_P of P is the complete graph on n nodes where the weight between nodes i and j is given by K(x_i, x_j). In this paper, we initiate the study of when...

While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, and divergent examples are known. We take a first step towards...

We recently proposed the "Lottery Ticket Hypothesis," which conjectures that the dense neural networks we typically train have much smaller subnetworks capable of training in isolation to the same accuracy starting from the original initialization...

Protein-based drugs are becoming some of the most important drugs of the XXI century. The typical mechanism of action of these drugs is a strong protein-protein interaction (PPI) between surfaces with complementary geometry and chemistry. Over the...

When high-quality labeled training data are unavailable, an alternative is to learn from training sources that are biased in some way. This talk will cover my group’s recent work on three problems where a learner has access to multiple biased...