102 citations · 267 across the 17 of their papers we have counts for
18 papers
Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers
Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie +1
Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel pr…
Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries
Divyat Mahajan, Sachin Goyal, Badr Youbi Idrissi +4
Next-token prediction (NTP) has driven the success of large language models (LLMs), but it struggles with long-horizon reasoning, planning, and creative writing, with these limitat…
Path-specific effects for pulse-oximetry guided decisions in critical care
Kevin Zhang, Yonghan Jung, Divyat Mahajan +2
Identifying and measuring biases associated with sensitive attributes is a crucial consideration in healthcare to prevent treatment disparities. One prominent issue is inaccurate p…
Learning to Defer for Causal Discovery with Imperfect Experts
Oscar Clivio, Divyat Mahajan, Perouz Taslakian +4
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not guaranteed to be correct. Expert recomm…
Compositional Risk Minimization
Divyat Mahajan, Mohammad Pezeshki, Charles Arnal +3
Compositional generalization is a crucial step towards developing data-efficient intelligent machines that generalize in human-like ways. In this work, we tackle a challenging form…
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
Divyat Mahajan, Jannes Gladrow, Agrin Hilmkil +2
Structural Causal Models (SCMs) offer a principled framework to reason about interventions and support out-of-distribution generalization, which are key goals in scientific discove…
Evaluating Interventional Reasoning Capabilities of Large Language Models
Tejas Kasetty, Divyat Mahajan, Gintare Karolina Dziugaite +2
Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consider using large language models (LLMs) to…
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
Sébastien Lachapelle, Divyat Mahajan, Ioannis Mitliagkas +1
We tackle the problems of latent variables identification and ``out-of-support'' image generation in representation learning. We show that both are possible for a class of decoders…
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Sébastien Lachapelle, Tristan Deleu, Divyat Mahajan +4
Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evi…
Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
Divyat Mahajan, Ioannis Mitliagkas, Brady Neal +1
We study the problem of model selection in causal inference, specifically for conditional average treatment effect (CATE) estimation. Unlike machine learning, there is no perfect a…
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 (…
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…
The Connection between Out-of-Distribution Generalization and Privacy of ML Models
Divyat Mahajan, Shruti Tople, Amit Sharma
With the goal of generalizing to out-of-distribution (OOD) data, recent domain generalization methods aim to learn "stable" feature representations whose effect on the output remai…
Split-Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions
Yanbo Xu, Divyat Mahajan, Liz Manrao +2
For many kinds of interventions, such as a new advertisement, marketing intervention, or feature recommendation, it is important to target a specific subset of people for maximizin…
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Ramaravind Kommiya Mothilal, Divyat Mahajan, Chenhao Tan +1
Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter pr…
Domain Generalization using Causal Matching
Divyat Mahajan, Shruti Tople, Amit Sharma
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective…
Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
Divyat Mahajan, Chenhao Tan, Amit Sharma
To construct interpretable explanations that are consistent with the original ML model, counterfactual examples---showing how the model's output changes with small perturbations to…
A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation
Varun Khare, Divyat Mahajan, Homanga Bharadhwaj +2
We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distribution…