Seminars Sorted by Series

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...

This talk considers the preference modeling problem and addresses the fact that pairwise comparison data often reflects irrational choice, e.g. intransitivity. Our key observation is that two items compared in isolation from other items may be...

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...

Deep neural networks have recently seen an impressive comeback with applications both in the public sector and the sciences. However, despite their outstanding success, a comprehensive theoretical foundation of deep neural networks is still missing...

In this talk, I will discuss my two recent works on Energy-Based Models. In the first work, I discuss how we can reinterpret standard classification architectures as class conditional energy-based models and train them using recently proposed...

We study sequential probabilistic prediction on data sequences which are not i.i.d., and even potentially generated by an adversary. At each round, the player assigns a probability distribution to possible outcomes and incurs the log-likelihood of...

This talk surveys the role of margins in the analysis of deep networks. As a concrete highlight, it sketches a perceptron-based analysis establishing that shallow ReLU networks can achieve small test error even when they are quite narrow, sometimes...

A common situation in Machine Learning is one where training data is not fully representative of a target population due to bias in the sampling mechanism or high costs in sampling the target population; in such situations, we aim to ’transfer’...

As deep learning systems become more prevalent in real-world applications it is essential to allow users to exert more control over the system. Exerting some structure over the learned representations enables users to manipulate, interpret, and even...

A continuing mystery in understanding the empirical success of deep neural networks has been in their ability to achieve zero training error and yet generalize well, even when the training data is noisy and there are many more parameters than data...

Meta-learning (or learning to learn) studies how to use machine learning to design machine learning methods themselves. We consider an optimization-based formulation of meta-learning that learns to design an optimization algorithm automatically...

There has been tremendous progress in designing accurate black-box prediction methods (boosting, random forests, bagging, neural nets, etc.) but for deployment in the real world, it is useful to quantify uncertainty beyond making point-predictions...

Modern deep generative models like GANs, VAEs and invertible flows are showing amazing results on modeling high-dimensional distributions, especially for images. We will show how they can be used to solve inverse problems by generalizing compressed...

Much real-world data is sampled at irregular intervals, but most time series models require regularly-sampled data. Continuous-time models address this problem, but until now only deterministic (ODE) models or linear-Gaussian models were efficiently...

We study boosting algorithms under the assumption that the given weak learner outputs hypotheses from a class of bounded capacity. This assumption is inspired by the common convention that weak hypotheses are “rules-of-thumbs” from an “easy-to-learn...

A possible high level description of statistical learning is that it aims to learn about some unknown probability distribution ("environment”) from samples it generates ("training data”). In its most general form, assuming no prior knowledge and...

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...

AlphaZero learns to play go, chess and shogi at a superhuman level through self play given only the rules of the game. This raises the question of whether a similar thing could be done for mathematics --- a MathZero. MathZero would require a formal...

In deep generative models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlinear map, such as a feedforward neural net, and add a small independent...

Epidemiological forecasting is critically needed for decision making by national and local governments, public health officials, healthcare institutions and the general public. The Delphi group at Carnegie Mellon University was founded in 2012 to...

Large-scale vision benchmarks have driven---and often even defined---progress in machine learning. However, these benchmarks are merely proxies for the real-world tasks we actually care about. How well do our benchmarks capture such tasks?

In this...

Langevin diffusions are continuous-time stochastic processes that are based on the gradient of a potential function. As such they have many connections---some known and many still to be explored---to gradient-based machine learning. I'll discuss...

In this talk I will discuss two lines of work involving learning in the presence of biased data and strategic behavior. In the first, we ask whether fairness constraints on learning algorithms can actually improve the accuracy of the classifier...

Some believe that truly effective and efficient reinforcement learning algorithms must explicitly construct and explicitly reason with models that capture the causal structure of the world. In short, model-based reinforcement learning is not...

In the last couple of years, a lot of progress has been made to enhance robustness of models against adversarial attacks. However, two major shortcomings still remain: (i) practical defenses are often vulnerable against strong “adaptive” attack...

An important problem today is how to allow multiple distributed entities to train a shared neural network on their private data while protecting data privacy. Federated learning is a standard framework for distributed deep learning Federated...

Data-driven design is making headway into a number of application areas, including protein, small-molecule, and materials engineering. The design goal is to construct an object with desired properties, such as a protein that binds to a target more...

Competitive optimization is needed for many ML problems such as training GANs, robust reinforcement learning, and adversarial learning. Standard approaches to competitive optimization involve each agent independently optimizing their objective...

We consider sequential prediction with expert advice when the data are generated stochastically, but the distributions generating the data may vary arbitrarily among some constraint set. We quantify relaxations of the classical I.I.D. assumption in...

In this talk I will introduce our next generation of graph neural networks. GNNs have the property that they are invariant to permutations of the nodes in the graph and to rotations of the graph as a whole. We claim this is unnecessarily restrictive...

Some of the aspects of the world around us are captured in natural language and refer to semantic high-level variables, which often have a causal role (referring to agents, objects, and actions or intentions). These high-level variables also seem to...

I will introduce Generalized Energy Based Models (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), which can learn the support of data with low intrinsic dimension in a...

For autonomous robots to operate in the open, dynamically changing world, they will need to be able to learn a robust set of skills from relatively little experience. This talk begins by introducing Grounded Simulation Learning as a way to bridge...