Oscar Key
6 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🐝 Cross-Pollinator (14) 🗺️ Taxonomy Completionist (19)
🐣
Hot Topic Early Bird
Conferences
ICML (2)
JMLR (2)
AISTATS (1)
NIPS (1)
Top co-authors
Research topics
Keywords
kernel methods
(2)
maximum mean discrepancy
(2)
efficient training
(1)
local learning
(1)
epistemic uncertainty
(1)
likelihood-free inference
(1)
sample complexity
(1)
interpretable machine learning
(1)
model parallelism
(1)
global optimization
(1)
hypothesis testing
(1)
signal-to-noise ratio
(1)
distributed training
(1)
batch selection
(1)
learning rate decay
(1)
approximate bayesian computation
(1)
reparameterization gradient
(1)
language model
(1)
gradient estimator
(1)
counterfactual explanation
(1)
Papers
Composite Goodness-of-fit Tests with Kernels
JMLR 2025
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
NIPS 2023
Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
ICML 2023
Interlocking Backpropagation: Improving depthwise model-parallelism
JMLR 2022
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
AISTATS 2021
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
ICML 2021