Upcoming Seminars

Deep Networks from First Principles

Fri, Jan 15, 2021, 4:30 pm
In this talk, we offer an entirely “white box’’ interpretation of deep (convolutional) networks from the perspective of data compression. In particular, we show how modern deep architectures, linear (convolution) operators and nonlinear activations, and parameters of each layer can be derived from the principle of rate reduction (and invariance).

Previous Seminars

Breaking the Sample Size Barrier in Statistical Inference and Reinforcement Learning

Tue, Dec 8, 2020, 11:00 am

A proliferation of emerging data science applications require efficient extraction of information from complex data. The unprecedented scale of relevant features, however, often overwhelms the volume of available samples, which dramatically complicates statistical inference and decision making.


HEE Seminar- Taylor Faucett-UCI-Physics Learning from Machines Learning

Tue, Dec 1, 2020, 2:00 pm

Machine Learning methods are extremely powerful but often function as black-box problem solvers, providing improved performance at the expense of clarity. Our work describes a new machine learning approach which translates the strategy of a deep neural network into simple functions that are meaningful and intelligible to the physicist, without...


Deep Learning: It’s Not All About Recognizing Cats and Dogs

Thu, Nov 12, 2020, 12:30 pm
In this seminar, we will examine the underinvested deep learning personalization and recommendation systems in the overall research community. The training of state-of-the-art industry-scale personalized and recommendation models consumes the highest number of compute cycles among all deep learning use cases. For AI inference, personalization and...

Analysis of Stochastic Gradient Descent in Continuous Time

Wed, Nov 4, 2020, 12:00 pm

Stochastic gradient descent is an optimisation method that combines classical gradient descent with random subsampling within the target functional. In this work, we introduce the stochastic gradient process as a continuous-time representation of stochastic gradient descent.


Consistency of Cheeger cuts: Total Variation, Isoperimetry, and Clustering

Wed, Oct 21, 2020, 12:00 pm

Clustering unlabeled point clouds is a fundamental problem in machine learning. One classical method for constructing clusters on graph-based data is to solve for Cheeger cuts, which balance between finding clusters that require cutting few graph edges and finding clusters which are similar in size.


CITP Seminar: Tal Zarsky – When Small Change Makes a Big Difference: Algorithmic Equity Among Similarly Situated Individuals

Tue, Oct 20, 2020, 12:30 pm

Please join the webinar here.


Online Optimization & Energy

Thu, Oct 15, 2020, 12:30 pm
Online optimization is a powerful framework in machine learning that has seen numerous applications to problems in energy and sustainability. In my group at Caltech, we began by applying online optimization to ‘right-size’ capacity in data centers nearly a decade ago; and by now tools from online optimization have been applied to develop...

Hydrological modeling in the era of big data and artificial intelligence

Wed, Oct 14, 2020, 8:00 pm
Nowadays, all sorts of sensors, from ground to space, collect a huge volume of data about the Earth. Recent advances in artificial intelligence (AI) provide unprecedented opportunities for data-driven hydrological modeling using such “Big Earth Data”. However, many critical issues remain to be addressed. For example, there lacks efficient...

Geometric Insights into Spectral Clustering by Graph Laplacian Embeddings

Wed, Sep 23, 2020, 12:00 pm

We present new theoretical results for procedures identifying coarse structures in a given data set by means of appropriate spectral embeddings. We combine ideas from spectral geometry, metastability, optimal transport, and spectral analysis of weighted graph Laplacians to describe the embedding geometry.


Towards a Secure Collaborative Learning Platform

Tue, Sep 22, 2020, 12:30 pm
Multiple organizations often wish to aggregate their sensitive data and learn from it, but they cannot do so because they cannot share their data. For example, banks wish to run joint anti-money laundering algorithms over their aggregate transaction data because criminals hide their traces across different banks. Bio: Raluca Ada Popa is an...