( events)   Timezone: »  
Sat Jul 29 12:00 PM -- 07:45 PM (PDT) @ Meeting Room 312 None
Sampling and Optimization in Discrete Space
Haoran Sun · Hanjun Dai · Priyank Jaini · Ruqi Zhang · Ellen Vitercik

There have recently been new research trends in efficient discrete sampling and optimization. We are organizing this workshop with the goals of 1) syncing up on the latest research progress in discrete sampling and optimization, 2) discussing the limitations of current methods and brainstorming new algorithm paradigms, and 3) connecting to applications in domains such as language/protein modeling, physics simulation, and bio/chemical engineering---where improved techniques for sampling/optimization in discrete space could help---and exploring the gaps between the application's needs and the capabilities of existing methods. We hope this workshop will be an excellent opportunity for presenting and discussing new algorithms and applications with researchers and practitioners within or outside the domain of discrete sampling/optimization.

Opening Remarks
Yoshua Bengio: GFlowNets for Bayesian Inference (Invited Talk)
Giacomo Zanella (Invited Talk)
Contributed Talk 1 (Contributed Talk)
Stefanie Jegelka: Learning discrete optimization: Loss functions and graph neural networks (Invited Talk)
Coffee Break (Break)
Poster Session 1 (Poster Session)
Will Grathwohl: Recent Applications of Gradients in Discrete Sampling (Invited Talk)
Lianhui Qin: Differentiable and structured text reasoning (Invited Talk)
Contributed Talk 2 (Contributed Talk)
Petar Veličković: The Melting Pot of Neural Algorithmic Reasoning (Invited Talk)
Closing Remarks (Closing Remark)
Poster Session 2 (Poster Session)
Constrained Sampling of Discrete Geometric Manifolds using Denoising Diffusion Probabilistic Models (Poster)
Efficient Location Sampling Algorithms for Road Networks (Poster)
Solving NP-hard Min-max Routing Problems as Sequential Generation with Equity Context (Poster)
Complex Preferences for Different Convergent Priors in Discrete Graph Diffusion (Poster)
Finite-state Offline Reinforcement Learning with Moment-based Bayesian Epistemic and Aleatoric Uncertainties (Poster)
Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information (Poster)
Guided Evolution with Binary Predictors for ML Program Search (Poster)
Understanding prompt engineering does not require rethinking generalization (Oral)
Sequential Attention for Feature Selection (Poster)
Tensor Proxies for Efficient Feature Cross Search (Poster)
SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems (Oral)
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning (Poster)
Discrete Diffusion Reward Guidance Methods for Offline Reinforcement Learning (Poster)
Protein Design with Guided Discrete Diffusion (Poster)
Optimizing protein fitness using Gibbs sampling with Graph-based Smoothing (Poster)
Tackling Provably Hard Representative Selection viaGraph Neural Networks (Oral)
Differentiable Search of Evolutionary Trees (Poster)
GFlowNets for Causal Discovery: an Overview (Poster)
Towards Accelerating Benders Decomposition via Reinforcement Learning Surrogate Models (Poster)
Topological Neural Discrete Representation Learning à la Kohonen (Oral)
Annealed Biological Sequence Optimization (Poster)
Reinforcement Learning for Sampling on Temporal Medical Imaging Sequences (Poster)
Categorical SDEs with Simplex Diffusion (Poster)
Training Discrete EBMs with Energy Discrepancy (Poster)
SOBER: Highly Parallel Bayesian Optimization and Bayesian Quadrature over Discrete and Mixed Spaces (Poster)
Hierarchical Decomposition Framework for Feasibility-hard Combinatorial Optimization (Poster)
Symmetric Exploration in Combinatorial Optimization is Free! (Poster)
Strictly Low Rank Constraint Optimization \\ --- An Asymptotically $\mathcal{O}(\frac{1}{t^2})$ Method (Poster)
An Optimal Clustering Algorithm for the Labeled Stochastic Block Model (Poster)
DISCS: A Benchmark for Discrete Sampling (Poster)
Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs (Oral)
Accelerating Diffusion-based Combinatorial Optimization Solvers by Progressive Distillation (Oral)
Efficient data selection employing Semantic Similarity-based Graph Structures for model training (Poster)
Can LLMs Generate Random Numbers? Evaluating LLM Sampling in Controlled Domains (Poster)
Diffusion on the Probability Simplex (Poster)
Global Optimality in Bivariate Gradient-based DAG Learning (Poster)