orals.md

title	Oral Sessions
layout	default
hide	true

<style> details { margin: 5pt; width: 400pt; } details > summary { border: none; cursor: pointer; font-weight: bold; } details > ul { } details[open] > summary { } </style>

{{ site.data.conference.short_name }} {{ site.data.conference.year }} Oral Sessions Schedule

All times are UTC. You can check current UTC time here and convert to other time zones using online time zones converters such as utctime.net or time.is. Be aware of the summer time change in Europe on March 27.

Day 1: Mon, March 28

(click on session titles to show the list of papers)

Session Title	Time (UTC)
Oral Session 1 | Learning theory / General ML Denoising and change point localisation in piecewise-constant high-dimensional regression coefficients Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably Survival regression with proper scoring rules and monotonic neural networks Multivariate Quantile Function Forecaster	08:30 - 09:30
Oral Session 2 | Bayesian methods / Sampling methods Differentiable Bayesian inference of SDE parameters using a pathwise series expansion of Brownian motion Nonparametric Relational Models with Superrectangulation Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap Unifying Importance Based Regularisation Methods for Continual Learning	09:30 - 10:30
Oral Session 3 | Causality / Trustworthy ML Almost optimal universal lower bound for learning causal DAGs with atomic interventions Variance Minimization in the Wasserstein Space for Invariant Causal Prediction On the Assumptions of Synthetic Control Methods Differentially Private Densest Subgraph	13:00 - 14:00
Oral Session 4 | Bandits / Reinforcement learning Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits Nonstochastic Bandits and Experts with Arm-Dependent Delays Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise Towards an Understanding of Default Policies in Multitask Policy Optimization	14:00 - 15:00

Day 2: Tue, March 29

(click on session titles to show the list of papers)

Session Title	Time (UTC)
Oral Session 5 | Kernels / Optimization / Deep learning Kernel Robust Smoothing A Single-Timescale Method for Stochastic Bilevel Optimization Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization Generative Models as Distributions of Functions	09:30 - 10:30
Oral Session 6 | Learning theory / Sampling methods Amortized Rejection Sampling in Universal Probabilistic Programming Adaptive Importance Sampling meets Mirror Descent : a Bias-variance tradeoff "Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose your Model, not your Loss Function" On the Consistency of Max-Margin Losses	10:30 - 11:30
Oral Session 7 | Bayesian methods / Deep learning "Many processors, little time: MCMC for partitions via optimal transport couplings" Rapid Convergence of Informed Importance Tempering Projection Predictive Inference for Generalized Linear and Additive Multilevel Models Density Ratio Estimation via Infinitesimal Classification	15:00 - 16:00

Day 3: Wed, March 30

(click on session titles to show the list of papers)

Session Title	Time (UTC)
Oral Session 8 | Learning theory / Sampling methods Sampling from Arbitrary Functions via PSD Models Orbital MCMC Hardness of Learning a Single Neuron with Adversarial Label Noise Data-splitting improves statistical performance in overparameterized regimes	07:00 - 08:00
Oral Session 9 | Reinforcement learning / Deep learning Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning "Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Gradient Temporal-Difference Learning" A general class of surrogate functions for stable and efficient reinforcement learning A Complete Characterisation of ReLU-Invariant Distributions	08:00 - 09:00
Oral Session 10 | Gaussian processes / Optimization / Online ML Minimax Optimization: The Case of Convex-Submodular Doubly Mixed-Effects Gaussian Process Regression Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes Debiasing Samples from Online Learning Using Bootstrap	13:00 - 14:00
Oral Session 11 | Bayesian methods / Sampling methods Entropy Regularized Optimal Transport Independence Criterion Two-Sample Test with Kernel Projected Wasserstein Distance Estimating Functionals of the Out-of-Sample Error Distribution in High-Dimensional Ridge Regression Heavy-tailed Streaming Statistical Estimation	14:00 - 15:00