Global Optimization in Wolfram Language: Solving Nonlinear and Nonconvex Problems
Explore advanced global optimization techniques in Wolfram Language for solving complex nonlinear and mixed-integer problems with real-world examples.
Mirror Diffusion Models for Constrained and Watermarked Generation
Explore Mirror Diffusion Models for generating data on constrained sets, enhancing watermarking capabilities, and improving AI safety in drug discovery applications.
Pursuit of Low-dimensional Structures in High-dimensional Data - 2013
Explore techniques for extracting low-dimensional structures from high-dimensional data, with applications in computer vision, image processing, and pattern recognition. Learn about convex optimization and regularization methods.
Duplicating Black Box Machine Learning Models
Exploración de técnicas avanzadas para duplicar modelos de aprendizaje automático de caja negra, destacando vulnerabilidades en servicios en la nube y proponiendo un nuevo método de ataque más eficiente.
Is Interaction Necessary for Distributed Private Learning?
Explores the necessity of interaction in locally differentially-private algorithms for convex optimization, presenting new algorithms and lower bounds on noninteractive approaches.
Wolfram Optimization - Overview and Advanced Techniques
Explore Wolfram's optimization functions for solving diverse problems, from convex to multidomain, with practical examples and advanced techniques.
Agnostic Proper Learning of Monotone Functions: Beyond the Black-Box Correction Barrier
Explore efficient algorithms for agnostic, proper learning of monotone Boolean functions, overcoming previous limitations and achieving near-optimal runtime complexity.
Error Bounds for Mean-Payoff Markov Decision Processes
Explore optimal transport techniques for error bounds in reinforcement learning, focusing on mean-payoff Markov decision processes and stochastic fixed point iterations.
A Fresh Look at Algorithms for Solving Smooth Multiobjective Optimization Problems
Explore new algorithms for smooth multiobjective optimization using linear programming to find decreasing directions, applicable to various constraint types and yielding substationary points.
Teaching Optimization: Comparing cvxpy, pyomo, and JuMP
Explore convex optimization modeling frameworks, comparing cvxpy, pyomo, and JuMP. Learn about common student challenges and how JuMP addresses them in undergraduate and graduate courses.
Set-limited Functions and Polynomial-time Interior-point Methods
Explore polynomial-time interior-point methods and set-limited functions with Yurri Nesterov, delving into advanced optimization techniques and mathematical theory.
Primal-Dual Optimization Methods for Robust Machine Learning
Explore primal-dual optimization techniques for enhancing machine learning robustness, focusing on advanced mathematical approaches to improve model performance and reliability.
Entropic Optimal Transport: Convergence Rates and ODE Characterization
Explore recent advances in entropic optimal transport, focusing on convergence rates and a novel ODE-based numerical method for multi-marginal problems. Gain insights into theoretical bounds and practical applications.
Inference and Uncertainty Quantification for Noisy Matrix Completion - Lecture 5
Explore inference and uncertainty quantification for noisy matrix completion, focusing on de-biased estimators and their distributional characterizations for optimal confidence interval construction.
Compatibility and the Lasso - Lecture 2
Explore compatibility and the Lasso in statistical learning with Sara van de Geer from ETH Zurich in this distinguished lecture on advanced machine learning techniques.
Fixed-point Error Bounds for Mean-payoff Markov Decision Processes
Explore optimal transport techniques for deriving finite-time error bounds in reinforcement learning, focusing on mean-payoff Markov decision processes and stochastic fixed point iterations.
Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter
Explore differentially private stochastic optimization techniques for loss functions with large worst-case Lipschitz parameters, addressing outliers and heavy-tailed data for improved excess risk bounds.
Sketching Semidefinite Programs for Super-Resolution Problems
Explore super-resolution problems, focusing on measure recovery from Fourier coefficients. Learn about sketching approaches to reduce semidefinite program size and algorithmic developments for integral bounds.
Optimal Transport for Distributionally Robust Optimization and Applications in Machine Learning
Explore optimal transport in distributionally robust optimization, focusing on its applications in machine learning, distribution shifts, and responsible AI. Gain insights into solving challenging optimization problems.
Stochastic Gradient Descent Methods with Biased Estimators
Explore recent advancements in stochastic gradient descent methods, focusing on biased estimators for large-scale optimization and minimax problems in machine learning applications.
Learning While Bidding in Vickrey Auctions with Acquisition Rate and Targeting Constraints
Explore optimization strategies for real-time bidding in Vickrey auctions, focusing on cost-minimization algorithms and stochastic approximation methods for ad placement campaigns with targeting constraints.