Devansh Arpit
16 papers · 2014–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (10) π Conference Polyglot (6) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(22)
π§
Keyword Pioneer
π₯
Mega-Team
(23)
π
Triple Crown
ποΈ
Keyword Collector
(50)
π
Conference Pioneer
π
Trend Setter
π
Century Club
(16)
π₯
Unstoppable
(9)
β
The Questioner
(2)
Conferences
ICLR (5)
ICML (5)
NIPS (3)
CLEAR (1)
JMLR (1)
PGM (1)
Top co-authors
Keywords
batch normalization
(2)
learning theory
(1)
anomaly detection
(1)
adversarial robustness
(1)
domain generalization
(1)
manifold learning
(1)
stochastic gradient descent
(1)
ensemble learning
(1)
feature extraction
(1)
subspace learning
(1)
causal discovery
(1)
sparse representation
(1)
dimensionality reduction
(1)
mean field approximation
(1)
fourier analysis
(1)
distributed computing
(1)
conditional entropy
(1)
time series forecasting
(1)
linear discriminant analysis
(1)
stochastic optimization
(1)
Papers
On the Unlikelihood of D-Separation
PGM 2024
Causal Layering via Conditional Entropy
CLEAR 2024
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
ICLR 2024
Merlion: End-to-End Machine Learning for Time Series
JMLR 2023
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
NIPS 2022
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
ICML 2021
The Break-Even Point on Optimization Trajectories of Deep Neural Networks
ICLR 2020
On the Spectral Bias of Neural Networks
ICML 2019
h-detach: Modifying the LSTM Gradient Towards Better Optimization
ICLR 2019
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets
NIPS 2019
Fraternal Dropout
ICLR 2018
Residual Connections Encourage Iterative Inference
ICLR 2018
A Closer Look at Memorization in Deep Networks
ICML 2017
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
ICML 2016
Why Regularized Auto-Encoders learn Sparse Representation?
ICML 2016
Dimensionality Reduction with Subspace Structure Preservation
NIPS 2014