Game-Enriched Categories
Explore game-enriched categories as an enhanced approach to modeling programming languages, potentially offering greater flexibility in strategy definition.
Formalizing the ∞-Categorical Yoneda Lemma
Explore the first formalization of ∞-category theory's Yoneda lemma using Rzk, a new proof assistant for synthetic ∞-category theory, paving the way for advanced mathematical proofs.
Univalent Double Categories - Formalization and Applications in Category Theory
Explore univalent double categories in category theory, their formalization in Coq, and applications in mathematics and computer science.
Learning on Graphs: From Representation to Minimally Supervised
Explore graph representation learning, from shallow to deep embedding, for heterogeneous data. Discover algorithms for temporal and dynamic graphs, and few-shot learning techniques for minimally supervised scenarios.
HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformers
Explore higher-order dynamic graph representation learning with efficient Transformers for improved link prediction in rapidly changing graphs. Learn about HOT model's architecture and performance.
Bayesian Inference of Causal Graphs: Current Status and Future Directions
Explore Bayesian inference for causal discovery, examining recent progress, challenges, and assumptions in modeling cause-effect relationships from observational data.
Robust and Sample-Efficient Simulation-Based Inference
Explore robust and sample-efficient methods for simulation-based inference, addressing model misspecification and computational limitations in scientific and engineering applications.
Functional Priors for Bayesian Deep Learning
Explore functional priors for Bayesian deep learning, focusing on imposing Gaussian process priors on neural networks through Wasserstein distance minimization.
Better Priors for Everyone - Choosing Prior Distributions in Bayesian Modeling
Explore techniques for choosing effective prior distributions in Bayesian modeling, including prior elicitation and automatic selection methods for improved statistical inference.
Parameter Estimation and Interpretability in Bayesian Mixture Models
Explore posterior contraction in Bayesian mixture modeling, examining parameter estimation and model interpretability under correct and misspecified conditions. Gain insights into tradeoffs between expressiveness and interpretability.
Independent Finite Approximations for Bayesian Nonparametric Inference
Explore independent finite approximations for Bayesian nonparametric inference, comparing them to truncated finite approximations and analyzing their performance in real-world applications.
Causality in Artificial Intelligence - Oral Session 3
Explore cutting-edge research in causal inference, including bounding effects, model reduction, interventions in games, and causally abstracted bandits.
All Causal DAGs Are Wrong but Some Are Useful
Explore the concept of causal DAGs, their usefulness, and challenges in causal discovery. Gain insights into evaluating causal models without ground truth and understanding causality's meaning across various tasks.
Causal Representation Learning and Optimal Intervention Design
Explore causal representation learning and optimal intervention design with Caroline Uhler's insightful keynote talk at UAI 2023.
Establishing Markov Equivalence in Cyclic Directed Graphs - UAI 2023 Oral Session 3
Explore an efficient procedure for establishing Markov equivalence in cyclic directed graphs, based on the Cyclic Equivalence Theorem and ancestral perspective.
Causal Representation Learning - Tutorial
Explore causal representation learning, combining machine learning with causal assumptions to identify causal variables from low-level data. Gain insights into core problems and future directions in scientific discovery.
Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning - Session 2
Explore critical analysis of uncertainty quantification in machine learning, examining conditional entropy and mutual information as measures for aleatoric and epistemic uncertainty.
Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty - UAI 2023 Oral Session 2
Explore the effectiveness of credal set volume as a measure of epistemic uncertainty in binary and multi-class classification, highlighting implications for machine learning.
Comparing Probability Distributions with Conditional Transport
Explore conditional transport as a new divergence for comparing probability distributions, with applications in generative modeling and resistance to mode collapse.
Convex Network Flows - Optimization Framework and Applications
Introducing a general framework for modeling flow problems over hyper graphs, with applications in network optimization, power flow, and wireless networks. Includes fast, parallelizable algorithm implementation in Julia.
What Does Machine Learning Have to Offer Mathematics? - Theoretically Speaking
Explore the intersection of machine learning and mathematics, focusing on novel techniques in combinatorics and potential impacts on mathematical practice.