Information-Theoretic Methods for Fair Risk Minimization
Explore information-theoretic approaches to fair risk minimization in machine learning, focusing on trustworthy AI and ethical considerations in algorithm design.
Differentially Quantized Gradient Methods
Explore advanced gradient quantization techniques for machine learning, focusing on differential methods and their impact on algorithm efficiency and performance.
Distribution Estimation With User-Level Privacy and Communication Constraints
Explore user-level privacy and communication constraints in distribution estimation, focusing on information-theoretic methods for trustworthy machine learning.
Information Constrained Optimal Transport
Explore information-constrained optimal transport theory and its applications in trustworthy machine learning with Stanford researcher Ayfer Ozgur.
Understanding Kubernetes Through Real-World Phenomena and Analogies
Explore Kubernetes design through real-world analogies, understanding its fundamental philosophies and how it tackles complexity in cloud-native systems.
Innovations in Theoretical Computer Science 2020 - Session 5
Explore cutting-edge research in theoretical computer science, including secure computation, communication protocols, coding theory, and fault-tolerant algorithms presented at ITCS 2020.
Diffusion, Probability, and the Age of Creative AI
Explore diffusion models in AI art generation, their information-theoretic foundation, and improvements in density estimation, interpretability, and sampling speed.
Learning Fast with No Goals - VISR Explained
Explore rapid generalization in Reinforcement Learning with VISR, focusing on successor features and goal-conditioned policies for efficient task adaptation without rewards.
The Arrow of Time in Causal Networks
Explore the macroscopic arrow of time, causal networks, and their relation to fundamental physics. Delve into entropy, complexity, and the nature of causality in our universe.
Coding Theoretic Framework for Private Information Retrieval - SIAM SAGA Seminar
Explore private information retrieval in coded storage systems, focusing on algebraic-geometric codes and star product schemes for adjustable storage overhead and server collusion protection.
Efficient, Stable Presentations From Error-Correcting Codes
Explore error-correcting codes and their applications in efficient, stable presentations with Columbia University's Henry Yuen in this insightful talk from the Fields Institute workshop.
Information Theoretic Indistinguishability via the Chi Squared Method
Explore information theoretic indistinguishability using the Chi squared method, covering problem overview, description, and conclusions in cryptography research.
PCPs and Global Hyper-contractivity - Lecture 1
Explore advanced concepts in theoretical computer science, focusing on Probabilistically Checkable Proofs and global hyper-contractivity with expert Dor Minzer.
Log-concave Polynomials and Spectral Independence - Part 3
Explore advanced concepts in log-concave polynomials and spectral independence, delving into their applications in analysis and theoretical computer science.
Log-concave Polynomials and Spectral Independence - Part 2
Explore advanced concepts in log-concave polynomials and spectral independence, delving into their applications in analysis and theoretical computer science.
Log-concave Polynomials and Spectral Independence - Part 1
Explore log-concave polynomials and spectral independence in this advanced mathematical analysis, delving into their applications in theoretical computer science.
PCPs and Global Hyper-contractivity - Lecture 2
Explore advanced concepts in PCPs and global hyper-contractivity with Dor Minzer, delving into complex mathematical theories and their applications in analysis and theoretical computer science.
PCPs and Global Hyper-contractivity - Lecture 1
Explore advanced concepts in theoretical computer science, focusing on Probabilistically Checkable Proofs and global hyper-contractivity with expert Dor Minzer.
Data Valuation: A Perturbation-Aware Approach
Explore perturbation-aware data valuation techniques for machine learning, focusing on information-theoretic methods to enhance trustworthiness and reliability in AI systems.
Memorization in Machine Learning
Explore information-theoretic methods for trustworthy machine learning, focusing on memorization techniques and their implications for model reliability and data privacy.
Approaching the Quantum Singleton Bound with Approximate Error Correction
Explore efficient quantum codes approaching the Singleton bound, using approximate recovery and quantum list decoding with folded Reed-Solomon codes for near-optimal error correction.