Goutham Rajendran
9 papers · 2021–2024 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(18)
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(8)
Core Methods
(7)
Artificial Intelligence
(5)
Core AI
(5)
Mathematics & Optimization
(3)
Optimization & Theory
(3)
Deep Learning
(2)
Mathematics
(2)
Optimization
(2)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Architectures
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Keywords
graphical model
(2)
latent variable
(2)
causal representation
(2)
causal inference
(2)
linear representation
(2)
latent variable model
(2)
structure learning
(1)
independent component analysis
(1)
transformer architecture
(1)
sparse principal component analysis
(1)
bregman divergence
(1)
system identification
(1)
gradient descent
(1)
exponential family
(1)
dimension reduction
(1)
contrastive learning
(1)
generative model
(1)
algorithm complexity
(1)
computational complexity
(1)
associative memory
(1)
Papers
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
CLeaR 2024
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
NeurIPS 2024
From Causal to Concept-Based Representation Learning
NeurIPS 2024
On the Origins of Linear Representations in Large Language Models
ICML 2024
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing
NeurIPS 2023
Identifiability of deep generative models without auxiliary information
NeurIPS 2022
Sub-exponential time Sum-of-Squares lower bounds for Principal Components Analysis
NeurIPS 2022
Learning latent causal graphs via mixture oracles
NeurIPS 2021
Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families
NeurIPS 2021