Thesis Defense - Lichen Zhang
- When
- America/New_York (EST)until 4:00 PM
- Where
- Building 3232 Vassar Street, Building 32, MA, 02139
Tickets are sold on Calendar. We link straight to the listing — nothing is bought here. Listing details come from the source and can change. Eventovia indexes events; it does not organize them or sell tickets. Terms & Disclaimer
Thesis Defense - Lichen Zhang takes place on Fri, Dec 4, 2026 at 3:00 PM (EST) at Building 32 in Cambridge, MA, and runs until 4:00 PM. Prices are shown on the Calendar listing.
About this event
Lichen Zhang presents a thesis on provably efficient algorithms for classical and modern machine learning via Zoom. The talk covers support vector machines, matrix completion, differential privacy, and quantum computing applications.
Čeština · Deutsch · Deutsch · Español · Español · Français · Français · Français · Italiano · 日本語 · 한국어 · Nederlands · Português · Português · 中文
Full description from organizerShow less
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
Keep going
All Cambridge events →Similar events
View all →









Details
- When
- Fri, Dec 4, 2026 · 3:00 PM (EST) · until 4:00 PM
- Where
- Building 32
- Address
- 32 Vassar Street, Building 32, MA, 02139
- Price
- See listing
Questions
- When is Thesis Defense - Lichen Zhang?
- Fri, Dec 4, 2026 at 3:00 PM EST.
- How much are tickets for Thesis Defense - Lichen Zhang?
- Prices are not published in the listing data; they are shown on Calendar.
- Where is Thesis Defense - Lichen Zhang?
- Building 32, 32 Vassar Street, Building 32, MA, 02139, Cambridge, MA.
- Where can I buy tickets for Thesis Defense - Lichen Zhang?
- Tickets are sold on Calendar. This page links straight to that listing; no tickets are sold here.
- What time does Thesis Defense - Lichen Zhang end?
- It runs until 4:00 PM.