Dissertation Talk: Measuring Generalization and Overfitting in Machine Learning

405 Soda Hall
  • Rebecca Roelofs
Due to the prevalence of machine learning (ML) algorithms and the potential for their decisions to profoundly impact billions of human lives, it is crucial that they are robust, reliable, and understandable. This thesis examines key theoretical pillars of ML surrounding generalization and overfitting, and tests the extent to which empirical behavior matches existing theory. We develop novel...

Between Shannon and Hamming: how bad can the channel be?: BLISS Seminar

540 Cory Hall
  • Anand Sarwate, Rutgers
The information theory community has traditionally studied two different models for communication. The Shannon-theoretic model treats the channel’s impact as random, so codes must correct almost all error patterns of a given weight; this is an average-case analysis. The coding-theoretic (Hamming-theoretic?) model treats the channel as adversarial, so codes must correct all error patterns of a...

Space Tech Symposium 2.0 at Berkeley: Hosted by Space Technologies at Cal

Sibley Auditorium, Bechtel Engineering Center
Come expand your network at Space Tech Symposium 2.0 @ Berkeley ( on May 6 by meeting researchers, CEOs of the hottest space startups, and Berkeley faculty as they discuss their visions for the future of space development. Mobility between space and non-space fields is at an all-time high and we'd love to have you join this conversation. Panelists from NASA,...

Dissertation Talk: On Systems and Algorithms for Distributed Machine Learning

521 Cory Hall
The advent of algorithms capable of leveraging vast quantities of data and computational resources has led to the proliferation of systems and tools aimed to facilitate the development and usage of these algorithms. Hardware trends, including the end of Moore's Law and the maturation of cloud computing, have placed a premium on the development of scalable algorithms designed for parallel...

Dissertation Talk: Approximation and Hardness: Beyond P and NP

310 Soda Hall
  • Pasin Manurangsi, University of California, Berkeley
The theory of NP-hardness of approximation has led to numerous tight characterizations of approximability of hard combinatorial optimization problems. Nonetheless, there are many fundamental problems which are out of reach for these techniques, such as problems that can be solved (or approximated) in quasi-polynomial time...

Dissertation Talk: Coded Illumination for Multidimensional Quantitative Phase Microscopy

Visual Computing Lab (VCL) Soda Hall
  • Michael Chen, UC Berkeley
Imaging biological samples under optical microscopes is challenging, since the absorption is too weak to form images with informative contrast. Besides fluorescent imaging techniques, label-free phase contrast imaging methods have been proposed to greatly improve the contrast of transparent samples. In order to efficiently recover quantitative properties, such as 2D phase projection and 3D...

Dissertation Talk: Realization of Integrated Coherent LiDAR

299 Cory Hall
  • Taehwan Kim, UC Berkeley
LiDAR (Light Detection and Ranging) captures high-definition real-time 3D images of the surrounding environment, which makes it a crucial sensing modality for applications such as self-driving cars. However, high price tag of existing commercial LiDAR modules based on mechanical beam scanners and intensity-based detection scheme prohibits them from being extensively applied to consumer products....

Dissertation Talk: Chip-Scale Fluorescence Microscope

490H (Immersion Room in Swarm Lab) Cory Hall
  • Efthymios Philip Papageorgiou
This talks presents a chip-scale fluorescence microscope for the detection of microscopic residual disease, small clusters of hundreds to thousands of cancer cells left behind after the gross tumor is removed during a surgical resection.

EECS Student Awards

Sibley Auditorium, Bechtel Engineering Center
Each year the EECS Student Awards Committee selects winners for each of our department awards, many based on nominations gathered from EECS students, faculty and staff.