Soham De
12 papers · 2017–2024 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🗺️ Taxonomy Completionist (22) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🧬 Topic Evolution
🧭
Keyword Pioneer
🚀
Conference Pioneer
🗃️
Keyword Collector
(55)
💎
Century Club · Bronze
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(11)
Optimization & Theory · Machine Learning
(8)
Architectures
(7)
Techniques
(5)
Optimization & Theory · Deep Learning
(4)
Artificial Intelligence
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Application Areas
(2)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Keywords
stochastic gradient descent
(4)
batch normalization
(4)
residual network
(3)
neural network optimization
(2)
skip connection
(2)
adversarial robustness
(2)
formal verification
(1)
adversarial training
(1)
model quantization
(1)
convex optimization
(1)
image classification
(1)
semidefinite programming
(1)
signal propagation
(1)
signal-to-noise ratio
(1)
lagrangian relaxation
(1)
non-convex optimization
(1)
adaptive learning rate
(1)
image recognition
(1)
adversarial attack
(1)
sequence modeling
(1)
Papers
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
ICML 2024
Resurrecting Recurrent Neural Networks for Long Sequences
ICML 2023
Characterizing signal propagation to close the performance gap in unnormalized ResNets
ICLR 2021
High-Performance Large-Scale Image Recognition Without Normalization
ICML 2021
On the Origin of Implicit Regularization in Stochastic Gradient Descent
ICLR 2021
Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks
NeurIPS 2020
On the Generalization Benefit of Noise in Stochastic Gradient Descent
ICML 2020
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
ICML 2020
Adversarial Robustness through Local Linearization
NeurIPS 2019
Efficient Neural Network Verification with Exactness Characterization
UAI 2019
Automated Inference with Adaptive Batches
AISTATS 2017
Training Quantized Nets: A Deeper Understanding
NeurIPS 2017