Seminars

Upcoming Seminars

Deep Networks from First Principles

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).
Speaker(s):
Yi Ma
University of California, Berkeley
Deep Networks from First Principles
View All Events

Previous Seminars

Breaking the Sample Size Barrier in Statistical Inference and Reinforcement Learning

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.

Speaker(s):
Yuting Wei
Carnegie Mellon University

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

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...

Speaker(s):
Taylor Faucett
UCI
Physics Learning from Machines Learning

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

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...
Speaker(s):
Carole-Jean Wu
Arizona State University

Analysis of Stochastic Gradient Descent in Continuous Time

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.

Speaker(s):

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

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.

Speaker(s):

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

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.

Speaker(s):
Tal Zarsky
University of Haifa – Faculty of Law

Online Optimization & Energy

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...
Speaker(s):
Adam Wierman
Caltech
Professor of Computing and Mathematical Sciences; Executive Officer for Computing and Mathematical Sciences; Director, Information Science and Technology

Hydrological modeling in the era of big data and artificial intelligence

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...
Speaker(s):
Yi Zheng
School of Environmental Science and Engineering at Southern University of Science and Technology

Geometric Insights into Spectral Clustering by Graph Laplacian Embeddings

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.

Speaker(s):
Franca Hoffman

Towards a Secure Collaborative Learning Platform

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...
Speaker(s):
Raluca Ada Popa
University of California, Berkeley

Pages