Multi-armed Bandits in Production at Stitch Fix
Explore scaling challenges and solutions for multi-armed bandits in online experimentation, including a new method for efficient, deterministic Thompson sampling at Stitch Fix.
MLOps for Deep Learning: Drift Detection and Efficient Retraining in Model Serving
Explore advanced MLOps techniques for deep learning, including drift detection, efficient retraining, and continuous deployment. Enhance model reliability and performance in production environments.
Provably Efficient Reinforcement Learning with Linear Function Approximation - Chi Jin
Explore efficient reinforcement learning with linear function approximation, covering key concepts like sample efficiency, value-based algorithms, and exploration in multi-armed bandits and linear MDPs.
Game Theoretic Learning and Spectrum Management - Part 2
Explore game theory in signal processing, covering multi-arm bandits, adaptive algorithms, and reinforcement learning for spectrum management and network optimization.
How Slot Machines Are Advancing the State of the Art in Computer Go AI
Explore Monte Carlo Tree Search in computer Go AI, covering its advantages, UCB1 strategy, and recent refinements like AMAF/RAVE, with insights into ongoing research topics.
Almost Optimal Variance-Constrained Best Arm Identification - Lecture 2
Explores advanced techniques in variance-constrained best arm identification, focusing on optimal algorithms and theoretical analysis for efficient decision-making in multi-armed bandit problems.
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.
Beyond Simple A/B Testing - Advanced Experimentation Tactics
Explore advanced A/B testing strategies like Multi-Armed Bandits and Switchback Experiments to enhance data-driven decision-making and product development.
Risk-Sensitive Bandits - Arm Mixtures Optimality and Regret-Efficient Algorithms
Delve into risk-aware sequential decision-making through distortion riskmetrics, exploring optimal arm mixture strategies and new algorithms for tracking these mixtures in multi-armed bandit problems.
Adaptive Multi-armed Bandit Algorithms for Markovian and IID Rewards
Explore adaptive multi-armed bandit algorithms and their applications in both Markovian and i.i.d reward scenarios, focusing on regret guarantees and novel algorithmic approaches.
Almost-Optimal Best Restless Markov Arm Identification with Fixed Confidence
Delve into advanced multi-armed bandit theory, focusing on identifying optimal arms in restless Markov chains through asymptotic analysis and policy optimization for distributed learning systems.
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Delve into stochastic combinatorial semi-bandits with a focus on risk-controlled online decision making, exploring algorithms for optimal subset selection while maintaining variance constraints.
Learning Optimal Beam Directions in Next-Generation Wireless Networks - A Fixed-Budget Stochastic Bandit Approach
Explore advanced beam direction optimization in mmWave and IRS technologies for 5G networks using Multi-Armed Bandits framework and fixed-budget algorithms to enhance wireless communication throughput.
Cost-Efficient Distributed Learning
Discover strategies for optimizing distributed gradient descent algorithms by managing worker responses and implementing adaptive techniques to balance computational efficiency with model quality in machine learning systems.
Advances in Risk-Aware Multi-Armed Bandit Problems - Lecture 3
Explore risk-aware multi-armed bandit problems with Vincent Tan. Learn advanced techniques for balancing exploration and exploitation in uncertain decision-making scenarios.
CS885: Multi-Armed Bandits
Explore multi-armed bandits, stochastic bandits, and online optimization strategies. Learn about exploration-exploitation trade-offs, regret, and epsilon-greedy approaches in practical applications.
Exploration with Limited Memory - Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits
Explore streaming algorithms for coin tossing, noisy comparisons, and multi-armed bandits, focusing on limited memory scenarios and efficient problem-solving techniques.
Learning With and From People - Collaborative Consumption Systems and User Engagement
Exploring collaborative consumption systems and incentivizing user behavior for improved system effectiveness, with focus on shared mobility and online marketplaces.
Bandits IV - Advanced Techniques in Multi-Armed Bandit Algorithms
Explore advanced bandit algorithms and their applications in machine learning with Kevin Jamieson from the University of Washington.
Bandits II - Advanced Algorithms and Applications
Explore advanced bandit algorithms and their applications in decision-making under uncertainty with Kevin Jamieson from the University of Washington.
ADR-X: ANN-Assisted Wireless Link Rate Adaptation for Compute-Constrained Embedded Gaming Devices
Innovative ANN-based rate adaptation technique for gaming consoles, reducing packet loss 10x while running 100x faster than existing solutions, enhancing wireless connectivity for controllers and headsets.