David Duvenaud
29 papers · 2013–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π Conference Polyglot (5)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Academic Marathon
(12)
π
Keyword Trendsetter Combo
(3)
π₯
Mega-Team
(34)
π
Triple Crown
π
Conference Pioneer
π
Century Club
(29)
π
Trend Setter
ποΈ
Keyword Collector
(99)
β‘
Prolific Year
(6)
π₯
Unstoppable
(5)
Conferences
ICML (10)
ICLR (9)
AISTATS (6)
ACL (2)
NIPS (2)
Top co-authors
Keywords
hyperparameter optimization
(4)
neural network
(3)
stochastic variational inference
(2)
neural network architecture
(2)
stochastic gradient descent
(2)
variational inference
(2)
bayesian neural network
(2)
stochastic differential equation
(2)
large language model
(2)
word embedding
(2)
energy-based model
(2)
gradient-based optimization
(2)
data augmentation
(1)
metropolis-hastings sampling
(1)
probabilistic modeling
(1)
network architecture
(1)
representation learning
(1)
density estimation
(1)
maximum likelihood
(1)
matrix factorization
(1)
Papers
Position: Humanity Faces Existential Risk from Gradual Disempowerment
ICML 2025
Many-shot Jailbreaking
NIPS 2024
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
NIPS 2024
Towards Understanding Sycophancy in Language Models
ICLR 2024
Experts Donβt Cheat: Learning What You Donβt Know By Predicting Pairs
ICML 2024
On Implicit Bias in Overparameterized Bilevel Optimization
ICML 2022
Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
AISTATS 2022
Complex Momentum for Optimization in Games
AISTATS 2022
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
ICLR 2021
Teaching with Commentaries
ICLR 2021
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
ICML 2021
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
ICML 2020
Optimizing Millions of Hyperparameters by Implicit Differentiation
AISTATS 2020
Scalable Gradients for Stochastic Differential Equations
AISTATS 2020
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
ICLR 2020
Your classifier is secretly an energy based model and you should treat it like one
ICLR 2020
FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
ICLR 2019
Explaining Image Classifiers by Counterfactual Generation
ICLR 2019
Understanding Undesirable Word Embedding Associations
ACL 2019
Towards Understanding Linear Word Analogies
ACL 2019
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
ICLR 2019
Invertible Residual Networks
ICML 2019
Noisy Natural Gradient as Variational Inference
ICML 2018
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
ICLR 2018
Inference Suboptimality in Variational Autoencoders
ICML 2018
Early Stopping as Nonparametric Variational Inference
AISTATS 2016
Gradient-based Hyperparameter Optimization through Reversible Learning
ICML 2015
Avoiding pathologies in very deep networks
AISTATS 2014
Structure Discovery in Nonparametric Regression through Compositional Kernel Search
ICML 2013