Show Detail |
Timezone: America/Los_Angeles |
Filter Rooms:
MON 28 MAR
midnight
1:30 a.m.
Orals 1:30-2:30
[1:30]
Denoising and change point localisation in piecewise-constant high-dimensional regression coefficients
[1:45]
Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably
[2:00]
Survival regression with proper scoring rules and monotonic neural networks
[2:15]
Multivariate Quantile Function Forecaster
(ends 2:30 AM)
2:30 a.m.
Orals 2:30-3:30
[2:30]
Differentiable Bayesian inference of SDE parameters using a pathwise series expansion of Brownian motion
[2:45]
Nonparametric Relational Models with Superrectangulation
[3:00]
Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap
[3:15]
Unifying Importance Based Regularisation Methods for Continual Learning
(ends 3:30 AM)
4:30 a.m.
Posters 4:30-6:00
(ends 6:00 AM)
6 a.m.
Orals 6:00-7:00
[6:00]
Almost Optimal Universal Lower Bound for Learning Causal DAGs with Atomic Interventions
[6:15]
Variance Minimization in the Wasserstein Space for Invariant Causal Prediction
[6:30]
On the Assumptions of Synthetic Control Methods
[6:45]
Differentially Private Densest Subgraph
(ends 7:00 AM)
7 a.m.
Orals 7:00-8:00
[7:00]
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
[7:15]
Nonstochastic Bandits and Experts with Arm-Dependent Delays
[7:30]
Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise
[7:45]
Towards an Understanding of Default Policies in Multitask Policy Optimization
(ends 8:00 AM)
9 a.m.
9:15 a.m.
Invited Talk:
Eric Tchetgen Tchetgen
(ends 10:15 AM)
10:15 a.m.
(ends 11:45 AM)
TUE 29 MAR
1 a.m.
Posters 1:00-2:30
(ends 2:30 AM)
2:30 a.m.
Orals 2:30-3:30
[2:30]
Adversarially Robust Kernel Smoothing
[2:45]
A Single-Timescale Method for Stochastic Bilevel Optimization
[3:00]
Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization
[3:15]
Generative Models as Distributions of Functions
(ends 3:30 AM)
3:30 a.m.
Orals 3:30-4:30
[3:30]
Amortized Rejection Sampling in Universal Probabilistic Programming
[3:45]
Adaptive Importance Sampling meets Mirror Descent : a Bias-variance Tradeoff
[4:00]
Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose Your Model, Not Your Loss Function
[4:15]
On the Consistency of Max-Margin Losses
(ends 4:30 AM)
5:30 a.m.
Community Activities and Mentorship:
(ends 7:00 AM)
7 a.m.
Invited Talk:
Laure Zanna
(ends 8:00 AM)
8 a.m.
Orals 8:00-9:00
[8:00]
Many processors, little time: MCMC for partitions via optimal transport couplings
[8:15]
Rapid Convergence of Informed Importance Tempering
[8:30]
Projection Predictive Inference for Generalized Linear and Additive Multilevel Models
[8:45]
Density Ratio Estimation via Infinitesimal Classification
(ends 9:00 AM)
9:45 a.m.
10 a.m.
Test Of Time:
(ends 11:00 AM)
11 a.m.
WED 30 MAR
midnight
Orals 12:00-1:00
[12:00]
Sampling from Arbitrary Functions via PSD Models
[12:15]
Orbital MCMC
[12:30]
Hardness of Learning a Single Neuron with Adversarial Label Noise
[12:45]
Data-splitting improves statistical performance in overparameterized regimes
(ends 1:00 AM)
1 a.m.
Orals 1:00-2:00
[1:00]
Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning
[1:15]
Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning
[1:30]
A general class of surrogate functions for stable and efficient reinforcement learning
[1:45]
A Complete Characterisation of ReLU-Invariant Distributions
(ends 2:00 AM)
2:30 a.m.
Invited Talk:
Mihaela van der Schaar
(ends 3:30 AM)
3:30 a.m.
6 a.m.
Orals 6:00-7:00
[6:00]
Minimax Optimization: The Case of Convex-Submodular
[6:15]
Doubly Mixed-Effects Gaussian Process Regression
[6:30]
Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes
[6:45]
Debiasing Samples from Online Learning Using Bootstrap
(ends 7:00 AM)
7 a.m.
Orals 7:00-8:00
[7:00]
Entropy Regularized Optimal Transport Independence Criterion
[7:15]
Two-Sample Test with Kernel Projected Wasserstein Distance
[7:30]
Estimating Functionals of the Out-of-Sample Error Distribution in High-Dimensional Ridge Regression
[7:45]
Heavy-tailed Streaming Statistical Estimation
(ends 8:00 AM)
8:30 a.m.
Posters 8:30-10:00
(ends 10:00 AM)
10 a.m.