Gradient Estimation with Stochastic Softmax Tricks

15 June 2020

Papers citing "Gradient Estimation with Stochastic Softmax Tricks"

50 / 62 papers shown

Title
Large (Vision) Language Models are Unsupervised In-Context Learners Artyom Gadetsky Andrei Atanov Yulun Jiang Zhitong Gao Ghazal Hosseini Mighan Amir Zamir Maria Brbić VLM MLLM LRM 64 0 0 03 Apr 2025
Soft Condorcet Optimization for Ranking of General Agents Marc Lanctot Kate Larson Michael Kaisers Quentin Berthet I. Gemp Manfred Diaz Roberto-Rafael Maura-Rivero Yoram Bachrach Anna Koop Doina Precup 37 0 0 31 Oct 2024
End-to-end Planner Training for Language Modeling Nathan Cornille Florian Mai Jingyuan Sun Marie-Francine Moens 23 0 0 16 Oct 2024
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers Anselm Paulus Georg Martius Vít Musil AI4CE 47 1 0 08 Jul 2024
Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model Longrong Yang Dong Shen Chaoxiang Cai Fan Yang Size Li Di Zhang Xi Li MoE 41 2 0 28 Jun 2024
Conditional Gumbel-Softmax for constrained feature selection with application to node selection in wireless sensor networks Thomas Strypsteen Alexander Bertrand 21 0 0 03 Jun 2024
End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty M. H. Dinh James Kotary Ferdinando Fioretto 20 0 0 12 Feb 2024
Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization James Kotary Jacob K Christopher M. H. Dinh Ferdinando Fioretto 6 0 0 28 Dec 2023
Compact Neural Graphics Primitives with Learned Hash Probing Towaki Takikawa Thomas Müller Merlin Nimier-David Alex Evans Sanja Fidler Alec Jacobson Alexander Keller 19 18 0 28 Dec 2023
Orchard: building large cancer phylogenies using stochastic combinatorial search E. Kulman R. Kuang Q. Morris 17 4 0 21 Nov 2023
Graph Deep Learning for Time Series Forecasting Andrea Cini Ivan Marisca Daniele Zambon C. Alippi AI4TS AI4CE 24 14 0 24 Oct 2023
A Model-Agnostic Graph Neural Network for Integrating Local and Global Information Wenzhuo Zhou Annie Qu Keiland W Cooper Norbert Fortin B. Shahbaba 23 1 0 23 Sep 2023
Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views Asif Khan Amos Storkey 17 1 0 19 Aug 2023
SynJax: Structured Probability Distributions for JAX Miloš Stanojević Laurent Sartran SyDa 13 4 0 07 Aug 2023
Efficient Learning of Discrete-Continuous Computation Graphs David Friede Mathias Niepert 13 3 0 26 Jul 2023
Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities Jayanta Mandi James Kotary Senne Berden Maxime Mulamba Víctor Bucarey Tias Guns Ferdinando Fioretto AI4CE 24 54 0 25 Jul 2023
Structured Dialogue Discourse Parsing Ta-Chung Chi Alexander I. Rudnicky 20 11 0 26 Jun 2023
Differentiable Clustering with Perturbed Spanning Forests Lawrence Stewart Francis R. Bach Felipe Llinares-López Quentin Berthet 21 8 0 25 May 2023
Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining Nicholas Monath Manzil Zaheer Kelsey R. Allen Andrew McCallum 22 6 0 27 Mar 2023
Backpropagation of Unrolled Solvers with Folded Optimization James Kotary M. H. Dinh Ferdinando Fioretto 16 14 0 28 Jan 2023
DAG Learning on the Permutahedron Valentina Zantedeschi Luca Franceschi Jean Kaddour Matt J. Kusner Vlad Niculae 22 11 0 27 Jan 2023
CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation Yiming Lei Zilong Li Yangyang Li Junping Zhang Hongming Shan 6 3 0 15 Jan 2023
Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes Marin Ballu Quentin Berthet 17 7 0 18 Nov 2022
Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization Thomas Effland Michael Collins 23 6 0 17 Oct 2022
SIMPLE: A Gradient Estimator for $k$ -Subset Sampling Kareem Ahmed Zhe Zeng Mathias Niepert Guy Van den Broeck BDL 21 24 0 04 Oct 2022
Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs Ðorðe Miladinovic Kumar Shridhar Kushal Kumar Jain Max B. Paulus J. M. Buhmann Mrinmaya Sachan Carl Allen DRL 21 5 0 26 Sep 2022
Structured Recognition for Generative Models with Explaining Away Changmin Yu Hugo Soulat Neil Burgess M. Sahani CML BDL 19 3 0 12 Sep 2022
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models Pasquale Minervini Luca Franceschi Mathias Niepert 38 11 0 11 Sep 2022
Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping Russell Z. Kunes Mingzhang Yin Max Land D. Haviv D. Pe’er Simon Tavaré BDL 6 2 0 12 Aug 2022
Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions Nikolaos Karalias Joshua Robinson Andreas Loukas Stefanie Jegelka 25 8 0 08 Aug 2022
Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation Haoyu Wang Nan Wu Hang Yang Cong Hao Pan Li 6 29 0 13 Jul 2022
Ordered Subgraph Aggregation Networks Chao Qian Gaurav Rattan Floris Geerts Christopher Morris Mathias Niepert 22 56 0 22 Jun 2022
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator Ting-Han Fan Ta-Chung Chi Alexander I. Rudnicky Peter J. Ramadge BDL 14 7 0 15 Jun 2022
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images Tom Ron M. Weiler-Sagie Tamir Hazan FAtt MedIm 16 6 0 06 Jun 2022
Backpropagation through Combinatorial Algorithms: Identity with Projection Works Subham S. Sahoo Anselm Paulus Marin Vlastelica Vít Musil Volodymyr Kuleshov Georg Martius 17 20 0 30 May 2022
Sparse Graph Learning from Spatiotemporal Time Series Andrea Cini Daniele Zambon C. Alippi CML AI4TS 35 18 0 26 May 2022
Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies Alon Berliner Guy Rotman Yossi Adi Roi Reichart Tamir Hazan BDL DRL 24 4 0 03 May 2022
Differentiable DAG Sampling Bertrand Charpentier Simon Kibler Stephan Günnemann 12 41 0 16 Mar 2022
Learning Group Importance using the Differentiable Hypergeometric Distribution Thomas M. Sutter Laura Manduchi Alain Ryser Julia E. Vogt 34 7 0 03 Mar 2022
Scaling Structured Inference with Randomization Yao Fu John P. Cunningham Mirella Lapata BDL 19 2 0 07 Dec 2021
Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces Kirill Struminsky Artyom Gadetsky D. Rakitin Danil Karpushkin Dmitry Vetrov BDL 11 9 0 28 Oct 2021
Learning with Algorithmic Supervision via Continuous Relaxations Felix Petersen Christian Borgelt Hilde Kuehne Oliver Deussen CLL 27 25 0 11 Oct 2021
A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning Iris A. M. Huijben W. Kool Max B. Paulus Ruud J. G. van Sloun 16 92 0 04 Oct 2021
Sparse Communication via Mixed Distributions António Farinhas Wilker Aziz Vlad Niculae André F. T. Martins 15 3 0 05 Aug 2021
DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning Hussein Hazimeh Zhe Zhao Aakanksha Chowdhery M. Sathiamoorthy Yihua Chen Rahul Mazumder Lichan Hong Ed H. Chi MoE 14 138 0 07 Jun 2021
Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach Ahmed Abbas Paul Swoboda 11 14 0 06 Jun 2021
Stochastic Iterative Graph Matching Linfeng Liu M. C. Hughes S. Hassoun Liping Liu 11 15 0 04 Jun 2021
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions Mathias Niepert Pasquale Minervini Luca Franceschi 21 81 0 03 Jun 2021
Learning to Extend Program Graphs to Work-in-Progress Code Xuechen Li Chris J. Maddison Daniel Tarlow 11 2 0 28 May 2021
Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication André F. T. Martins 11 1 0 01 Apr 2021