44 citations · 183 across the 34 of their papers we have counts for
38 papers
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…
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…
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…
Reusable Slotwise Mechanisms
Trang Nguyen, Amin Mansouri, Kanika Madan +4
Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generalization in novel scenarios. However, achi…
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…
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…
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…
Interventional Causal Representation Learning
Kartik Ahuja, Divyat Mahajan, Yixin Wang +1
Causal representation learning seeks to extract high-level latent factors from low-level sensory data. Most existing methods rely on observational data and structural assumptions (…
Weakly Supervised Representation Learning with Sparse Perturbations
Kartik Ahuja, Jason Hartford, Yoshua Bengio
The theory of representation learning aims to build methods that provably invert the data generating process with minimal domain knowledge or any source of supervision. Most prior…
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…
Why does Throwing Away Data Improve Worst-Group Error?
Kamalika Chaudhuri, Kartik Ahuja, Martin Arjovsky +1
When facing data with imbalanced classes or groups, practitioners follow an intriguing strategy to achieve best results. They throw away examples until the classes or groups are ba…
Towards efficient representation identification in supervised learning
Kartik Ahuja, Divyat Mahajan, Vasilis Syrgkanis +1
Humans have a remarkable ability to disentangle complex sensory inputs (e.g., image, text) into simple factors of variation (e.g., shape, color) without much supervision. This abil…
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
Jean-Christophe Gagnon-Audet, Kartik Ahuja, Mohammad-Javad Darvishi-Bayazi +3
Machine learning models often fail to generalize well under distributional shifts. Understanding and overcoming these failures have led to a research field of Out-of-Distribution (…
Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
Amit Dhurandhar, Karthikeyan Ramamurthy, Kartik Ahuja +1
Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants h…
Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning
Kartik Ahuja, Jason Hartford, Yoshua Bengio
A key goal of unsupervised representation learning is "inverting" a data generating process to recover its latent properties. Existing work that provably achieves this goal relies…
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Dinghuai Zhang, Kartik Ahuja, Yilun Xu +2
Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer fo…
Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
Abhin Shah, Karthikeyan Shanmugam, Kartik Ahuja
Treatment effect estimation from observational data is a fundamental problem in causal inference. There are two very different schools of thought that have tackled this problem. On…
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang +4
The invariance principle from causality is at the heart of notable approaches such as invariant risk minimization (IRM) that seek to address out-of-distribution (OOD) generalizatio…
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
Soroosh Shahtalebi, Jean-Christophe Gagnon-Audet, Touraj Laleh +3
A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i.i.d to the training…
Treatment Effect Estimation using Invariant Risk Minimization
Abhin Shah, Kartik Ahuja, Karthikeyan Shanmugam +3
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias. In…
Learning to Initialize Gradient Descent Using Gradient Descent
Kartik Ahuja, Amit Dhurandhar, Kush R. Varshney
Non-convex optimization problems are challenging to solve; the success and computational expense of a gradient descent algorithm or variant depend heavily on the initialization str…
Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions
Kartik Ahuja, Karthikeyan Shanmugam, Amit Dhurandhar
Recently, invariant risk minimization (IRM) (Arjovsky et al.) was proposed as a promising solution to address out-of-distribution (OOD) generalization. In Ahuja et al., it was show…
Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Kartik Ahuja, Jun Wang, Amit Dhurandhar +2
Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be pref…
Adversarial Feature Desensitization
Pouya Bashivan, Reza Bayat, Adam Ibrahim +5
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's perform…