activity
20152023
most citedSAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization

22 citations · 81 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

25 papers · 1 filter

cs.LG2023

Multi-Domain Causal Representation Learning via Weak Distributional Invariances

Kartik Ahuja, Amin Mansouri, Yixin Wang

Causal representation learning has emerged as the center of action in causal machine learning research. In particular, multi-domain datasets present a natural opportunity for showc…

cs.LG2023

On the Identifiability of Quantized Factors

Vitória Barin-Pacela, Kartik Ahuja, Simon Lacoste-Julien +1

Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the theory of identifiability. The identifia…

cs.LG2023

A Closer Look at In-Context Learning under Distribution Shifts

Kartik Ahuja, David Lopez-Paz

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language…

cs.LG2022★ 5 cited

Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

Alexandre Ramé, Kartik Ahuja, Jianyu Zhang +3

Foundation models are redefining how AI systems are built. Practitioners now follow a standard procedure to build their machine learning solutions: from a pre-trained foundation mo…

cs.LG2022★ 3 cited

Empirical Study on Optimizer Selection for Out-of-Distribution Generalization

Hiroki Naganuma, Kartik Ahuja, Shiro Takagi +5

Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution. While much promising work has been acco…

cs.LG2022★ 2 cited

FL Games: A Federated Learning Framework for Distribution Shifts

Sharut Gupta, Kartik Ahuja, Mohammad Havaei +2

Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. However, participating clients typically each h…