Abstract: I will talk about a recent large-scale effort to provide novel estimates of the social cost of greenhouse gas emissions. I will touch on three aspects: The first part will introduce the concept of the social cost of carbon and other greenhouse gases and give a brief overview of its use in the policy…
For the tenth year, MIT and Microsoft New England are proud to collaborate with Women in Data Science (WiDS) Worldwide to bring the WiDS regional conference to Cambridge, Massachusetts. This one-day conference will feature an all-female lineup of speakers and panelists from academia and industry to talk about the latest data science-related research in a number of domains, and to learn how leading-edge researchers and companies are leveraging data science for success.
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…
Abstract: I will talk about a recent large-scale effort to provide novel estimates of the social cost of greenhouse gas emissions. I will touch on three aspects: The first part will introduce the concept of the social cost of carbon and other greenhouse gases and give a brief overview of its use in the policy…
For the tenth year, MIT and Microsoft New England are proud to collaborate with Women in Data Science (WiDS) Worldwide to bring the WiDS regional conference to Cambridge, Massachusetts. This one-day conference will feature an all-female lineup of speakers and panelists from academia and industry to talk about the latest data science-related research in a number of domains, and to learn how leading-edge researchers and companies are leveraging data science for success.
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
