March 1, 2023
Behrooz Tahmasebi (CSAIL)
In practice, encoding invariances into models helps sample complexity. In this work, we tighten and generalize theoretical results on how invariances improve sample complexity. In particular, we provide minimax optimal rates for kernel ridge...
March 8, 2023
Sarah Cen (LIDS)
We propose a generalization of the synthetic controls and synthetic interventions methodology to incorporate network interference. We consider the estimation of unit-specific treatment effects from panel data where there are spillover effects across...
March 15, 2023
Abhin Shah (LIDS & EECS)
We consider learning a fair predictive model when sensitive attributes are uncertain, say, due to a limited amount of labeled data, collection bias, or privacy mechanism. We formulate the problem, for the independence notion of fairness, using the...
March 22, 2023
Zeyu Jia (LIDS & EECS)
We consider the question of estimating multi-dimensional Gaussian mixtures (GM) with compactly supported or subgaussian mixing distributions. Minimax estimation rate for this class (under Hellinger, TV and KL divergences) is a long-standing open...
April 5, 2023
Moïse Blanchard ()
We give query complexity lower bounds for convex optimization and the related feasibility problem. We show that quadratic memory is necessary to achieve the optimal oracle complexity for first-order convex optimization. In particular, this shows...
April 12, 2023
Raaz Dwivedi ()
We introduce an improved variant of nearest neighbors for counterfactual inference in panel data settings where multiple units are assigned multiple treatments over multiple time points, each sampled with constant probabilities. We call this...
April 19, 2023
Sylvie Koziel (LIDS)
Taking decisions requires information and data. The more data the better the decisions. From machine learning to artificial intelligence and internet-of-things, data, and especially big data, plays a central part in today's applications and research...
April 26, 2023
Anzo Teh (LIDS)
We consider a problem of estimating means of n multivariate Poisson distributed random variables. Our methodological contribution is a new empirical Bayes approach that directly optimizes a regression function from observations to predicted means by...
May 2, 2023
Alessandro Zanardi (ETH Zurich & LIDS)
Modern robotics often entails multiple embodied agents operating in a shared environ- ment. But making optimal decisions in such cases results to be much harder than the single-agent counterpart, often the complexity grows almost exponentially in...
May 3, 2023
Sung Min (Sam) Park (CSAIL)
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy....
May 9, 2023
Daniel Shen (LIDS)
To achieve decarbonization goals, the grid will need to integrate large amounts of renewable energy and manage the uncertainties associated with their generation forecasts. These uncertainties could either be managed through the central system...
May 16, 2023
Charles Dawson (LIDS)
Recent years have seen large numbers of learning-enabled autonomous systems, especially autonomous vehicles and drones, deployed in the real world. Unfortunately, these deployments have been accompanied by a corresponding increase in safety-critical...
May 23, 2023
Yifu Ding (MITEI)
Networked microgrids aggregate distributed energy resources and flexible loads to reach the minimum capacity for market participation and provide reserve services for the grid. However, due to uncertain renewable generations such as solar power,...