Show Detail » |
Timezone: America/Los_Angeles |

Filter Events:

Filter Rooms:

MON 24 APR

8 a.m.

(ends 11:00 AM)

10 p.m.

(ends 8:00 AM)

11:45 p.m.

TUE 25 APR

midnight

1 a.m.

Coffee Break

1:30 a.m.

Oral
s
1:30-2:30

[1:30]
The Schrödinger Bridge between Gaussian Measures has a Closed Form

[1:45]
Rethinking Initialization of the Sinkhorn Algorithm

[2:00]
Using Sliced Mutual Information to Study Memorization and Generalization in Deep Neural Networks

[2:15]
Mode-Seeking Divergences: Theory and Applications to GANs

(ends 2:30 AM)

2:30 a.m.

3:30 a.m.

Lunch Break

5 a.m.

Oral
s
5:00-6:00

[5:00]
Who Should Predict? Exact Algorithms For Learning to Defer to Humans

[5:15]
Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

[5:30]
Origins of Low-Dimensional Adversarial Perturbations

[5:45]
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning

(ends 6:00 AM)

6 a.m.

Coffee Break

6:30 a.m.

Oral
s
6:30-7:30

[6:30]
The Power of Recursion in Graph Neural Networks for Counting Substructures

[6:45]
Implicit Graphon Neural Representation

[7:00]
Implications of sparsity and high triangle density for graph representation learning

[7:15]
Fitting low-rank models on egocentrically sampled partial networks

(ends 7:30 AM)

7:30 a.m.

(ends 10:00 AM)

9 a.m.

10 p.m.

(ends 8:00 AM)

WED 26 APR

midnight

Invited Talk:

Shakir Mohamed

(ends 1:00 AM)

1 a.m.

Coffee Break

1:30 a.m.

Oral
s
1:30-2:30

[1:30]
Do Bayesian Neural Networks Need To Be Fully Stochastic?

[1:45]
Indeterminacy in Generative Models: Characterization and Strong Identifiability

[2:00]
Distance-to-Set Priors and Constrained Bayesian Inference

[2:15]
Particle algorithms for maximum likelihood training of latent variable models

(ends 2:30 AM)

2:30 a.m.

Oral
s
2:30-3:30

[2:30]
BaCaDI: Bayesian Causal Discovery with Unknown Interventions

[2:45]
Multilevel Bayesian Quadrature

[3:00]
Discovering Many Diverse Solutions with Bayesian Optimization

[3:15]
Inducing Point Allocation for Sparse Gaussian Processes in High-Throughput Bayesian Optimisation

(ends 3:30 AM)

3:30 a.m.

Lunch Break

5 a.m.

6 a.m.

Coffee Break

6:30 a.m.

Oral
s
6:30-7:30

[6:30]
Huber-robust confidence sequences

[6:45]
Error Estimation for Random Fourier Features

[7:00]
A Tale of Sampling and Estimation in Discounted Reinforcement Learning

[7:15]
Safe Sequential Testing and Effect Estimation in Stratified Count Data

(ends 7:30 AM)

7:30 a.m.

(ends 10:00 AM)

10 p.m.

(ends 3:00 AM)

11 p.m.

THU 27 APR

midnight

Invited Talk:

Tamara Broderick

(ends 1:00 AM)

1 a.m.

Coffee Break

1:30 a.m.

Oral
s
1:30-2:30

[1:30]
Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation

[1:45]
Fix-A-Step: Semi-supervised Learning From Uncurated Unlabeled Data

[2:00]
Blessing of Class Diversity in Pre-training

[2:15]
Federated Learning under Distributed Concept Drift

(ends 2:30 AM)

2:30 a.m.

Oral
s
2:30-3:30

[2:30]
Scalable Bicriteria Algorithms for Non-Monotone Submodular Cover

[2:45]
Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate

[3:00]
An Efficient and Continuous Voronoi Density Estimator

[3:15]
Hedging against Complexity: Distributionally Robust Optimization with Parametric Approximation

(ends 3:30 AM)

3:30 a.m.

Lunch Break

5 a.m.

(ends 7:30 AM)