This is a joint talk with CSAIL’s Theory of Computation Colloquium. Abstract: Over the last few years, graph-based approaches to nearest neighbor search have attracted renewed interest. Algorithms such as HNSW, NSG, and DiskANN have become popular tools in practice. These algorithms are highly versatile and come with efficient implementations. At the same time, their correctness,…

Abstract: Mean-field variational inference (MFVI) approximates a target distribution with a product distribution in the standard coordinate system, offering a scalable approach to Bayesian inference but often severely underestimating uncertainty due to neglected dependence. We show that MFVI can be greatly improved when performed along carefully chosen principal component axes rather than the standard coordinates.…

Abstract: Modern large language models have billions to trillions of parameters, creating enormous computational and memory costs. Quantization, i.e. reducing their numerical precision, is the leading practical mitigation strategy. But how far can we push it, and what do we lose? This talk addresses different sides of this question. First, for post-training quantization, we characterize…

TBD