Cambridge, MA
Community & networking

Thesis Defense - Lichen Zhang

Register with organizer
Thesis Defense - Lichen Zhang event artwork
The gathering

What to look forward to

Lichen Zhang will present efficient, provably correct algorithms spanning support vector machines, matrix completion, adaptive data structures, and quantum coreset construction. The talk will highlight near-linear runtimes, robustness through differential privacy, and query-efficiency guarantees grounded in randomized linear algebra and optimization.

From the organizer

Inside the event

Speaker: Lichen Zhang Title: Provably Efficient Algorithms for Classical and Modern Machine Learning Abstract: Modern machine learning relies largely on efficient heuristics without provable guarantees, while provable algorithms are often slow or depend on unrealistic assumptions. In this thesis, we design algorithms for machine learning problems that are both efficient and provably correct, using tools from randomized linear algebra, continuous optimization, differential privacy and quantum computing. We start with two classical problems: support vector machines and matrix completion. We train linear support vector machines to high accuracy in time nearly linear in the number of data points, where previous high-accuracy methods took superlinear time. For matrix completion, the problem behind recommender systems, we show that alternating minimization, the method used in practice, still converges when each step is solved only approximately, so it runs in nearly the time it takes to verify an answer. We then turn to modern settings. Learning algorithms often query randomized data structures, such as nearest neighbor indexes, with queries that depend on earlier answers. Using differential privacy, we make such data structures robust to these adaptive queries with far fewer independent copies than before. Finally, we give a quantum algorithm that builds coresets, which are small weighted summaries of large data sets, while querying only a sublinear number of points, and we show that this number of queries is essentially optimal for generic sensitivity sampling. Zoom Link: https://mit.zoom.us/j/8587512838

Meet in Cambridge, MA

City view. The source has not supplied a venue; check the organizer for the exact location.

Open in Google Maps ↗

Details come from the event listing; registration is managed by the organizer.

Last checked: Nov 19, 2026. Confirm current availability before making plans.

Superpower Daily

Stay curious between events.

AI news, useful tools, and handpicked events in your inbox.

YOUR READING SPACE

Notifications