Skip to yearly menu bar Skip to main content

Workshop: OPT 2023: Optimization for Machine Learning

Poster Session 2

Xiao-Yang Liu · Guy Kornowski · Philipp Dahlinger · Abbas Ehsanfar · Binyamin Perets · David Martinez-Rubio · Sudeep Raja Putta · Runlong Zhou · Connor Lawless · Julian J Stier · Chen Fan · Michal Ĺ ustr · James Spann · Jung Hun Oh · Yao Xie · Qi Zhang · Krishna Acharya · Sourabh Medapati · Sharan Vaswani · Sruthi Gorantla · Mohamed Elsayed · Hongyang Zhang · Reza Asad · Viktor Pavlovic · Betty Shea · Georgy Noarov · Chuan He · Daniil Vankov · Taoan Huang · Michael Lu · Anant Mathur · Konstantin Mishchenko · Stanley Wei · Francesco Faccio · Yuchen Zeng · Tianyue Zhang · Chris Junchi Li · Aaron Mishkin · Sina Baharlouei · Chen Xu · Sasha Abramowitz · Sebastian Stich · Felix Dangel

[ ]
Fri 15 Dec 1 p.m. PST — 2 p.m. PST


Posters in this session:

  • K-Spin Ising Model for Combinatorial Optimizations over Graphs: An Reinforcement Learning Approach

  • An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization

  • Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization

  • Exploring Modern Evolution Strategies in Portfolio Optimization

  • Unnormalized Density Estimation with Root Sobolev Norm Regularization

  • Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

  • Regret Bounds for Optimistic Follow The Leader: Applications in Portfolio Selection and Linear Regression

  • How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization

  • Fair Minimum Representation Clustering

  • FaDE: Fast DARTS Estimator on Hierarchical NAS Spaces

  • MSL: An Adaptive Momentem-based Stochastic Line-search Framework

  • Global CFR: Meta-Learning in Self-Play Regret Minimization

  • (Un)certainty selection methods for Active Learning on Label Distributions

  • Optimal Transport for Kernel Gaussian Mixture Models

  • Large-scale Non-convex Stochastic Constrained Distributionally Robust Optimization

  • Oracle Efficient Algorithms for Groupwise Regret

  • Adaptive Gradient Methods at the Edge of Stability

  • Reducing Predict and Optimize to Convex Feasibility

  • Optimizing Group-Fair Plackett-Luce Ranking Models for Relevance and Ex-Post Fairness

  • Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning

  • Noise Stability Optimization for Flat Minima with Tight Rates

  • Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism

  • Accelerated gradient descent: A guaranteed bound for a heuristic restart strategy

  • Noise-adaptive (Accelerated) Stochastic Heavy-Ball Momentum

  • Greedy Newton

  • High-Dimensional Prediction for Sequential Decision Making

  • A proximal augmented Lagrangian based algorithm for federated learning with constraints

  • Last Iterate Convergence of Popov Method for Non-monotone Stochastic Variational Inequalities

  • Contrastive Predict-and-Search for Mixed Integer Linear Programs

  • Practical Principled Policy Optimization for Finite MDPs

  • Feature Selection in Generalized Linear models via the Lasso: To Scale or Not to Scale?

  • Noise Injection Irons Out Local Minima and Saddle Points

  • On the Synergy Between Label Noise and Learning Rate Annealing in Neural Network Training

  • Continually Adapting Optimizers Improve Meta-Generalization

  • The Expressive Power of Low-Rank Adaptation

  • From 6235149080811616882909238708 to 29: Vanilla Thompson Sampling Revisited

  • Accelerating Inexact HyperGradient Descent for Bilevel Optimization

  • A novel analysis of gradient descent under directional smoothness

  • f-FERM: A Scalable Framework for Robust Fair Empirical Risk

  • An alternative approach to train neural networks using monotone variational inequality

  • Generalisable Agents for Neural Network Optimisation

  • On the Convergence of Local SGD Under Third-Order Smoothness and Hessian Similarity

  • Diversity-adjusted adaptive step size

  • Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets

Chat is not available.