Search Results for author: Amit Sharma

Found 36 papers, 13 papers with code

Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost

no code implementations27 Jun 2023 Parikshit Bansal, Amit Sharma

Instead, we propose a sampling strategy based on the difference in prediction scores between the base model and the finetuned NLP model, utilizing the fact that most NLP models are finetuned from a base model.

Active Learning Semantic Similarity +1

Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes

no code implementations19 Jun 2023 Abhinav Kumar, Amit Deshpande, Amit Sharma

We prove that our method only requires that the ranking of estimated causal effects is correct across attributes to select the correct classifier.

Rethinking Counterfactual Data Augmentation Under Confounding

no code implementations29 May 2023 Abbavaram Gowtham Reddy, Saketh Bachu, Saloni Dash, Charchit Sharma, Amit Sharma, Vineeth N Balasubramanian

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data for a machine learning model.

Data Augmentation

Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers

no code implementations26 May 2023 Parikshit Bansal, Amit Sharma

Therefore, using methods from the causal inference literature, we propose an algorithm to regularize the learnt effect of the features on the model's prediction to the estimated effect of feature on label.

Causal Inference

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

no code implementations28 Apr 2023 Emre Kiciman, Robert Ness, Amit Sharma, Chenhao Tan

The causal capabilities of large language models (LLMs) is a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy.

Causal Discovery Common Sense Reasoning

Counterfactual Generation Under Confounding

no code implementations22 Oct 2022 Abbavaram Gowtham Reddy, Saloni Dash, Amit Sharma, Vineeth N Balasubramanian

Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors.

Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems

no code implementations7 Oct 2022 Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma

To explain this generalization failure, we consider an intervention-based importance metric, which shows that a fine-tuned model captures spurious correlations and fails to learn the causal features that determine the relevance between any two text inputs.

Language Modelling Out-of-Distribution Generalization +3

The Counterfactual-Shapley Value: Attributing Change in System Metrics

no code implementations17 Aug 2022 Amit Sharma, Hua Li, Jian Jiao

Specifically, we propose a method to estimate counterfactuals using time-series predictive models and construct an attribution score, CF-Shapley, that is consistent with desirable axioms for attributing an observed change in the output metric.

Time Series Analysis

Probing Classifiers are Unreliable for Concept Removal and Detection

no code implementations8 Jul 2022 Abhinav Kumar, Chenhao Tan, Amit Sharma

Even under the most favorable conditions for learning a probing classifier when a concept's relevant features in representation space alone can provide 100% accuracy, we prove that a probing classifier is likely to use non-concept features and thus post-hoc or adversarial methods will fail to remove the concept correctly.


Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization

no code implementations15 Jun 2022 Jivat Neet Kaur, Emre Kiciman, Amit Sharma

Based on the relationship between spurious attributes and the classification label, we obtain realizations of the canonical causal graph that characterize common distribution shifts and show that each shift entails different independence constraints over observed variables.

Domain Generalization Out-of-Distribution Generalization

Machine Explanations and Human Understanding

1 code implementation8 Feb 2022 Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan

Our key result is that without assumptions about task-specific intuitions, explanations may potentially improve human understanding of model decision boundary, but they cannot improve human understanding of task decision boundary or model error.

Decision Making Open-Ended Question Answering

Deep End-to-end Causal Inference

1 code implementation4 Feb 2022 Tomas Geffner, Javier Antoran, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang

Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.

Causal Discovery Causal Inference +1

Long Story Short: Omitted Variable Bias in Causal Machine Learning

no code implementations26 Dec 2021 Victor Chernozhukov, Carlos Cinelli, Whitney Newey, Amit Sharma, Vasilis Syrgkanis

Therefore, simple plausibility judgments on the maximum explanatory power of omitted variables (in explaining treatment and outcome variation) are sufficient to place overall bounds on the size of the bias.

BIG-bench Machine Learning Causal Inference

Matching Learned Causal Effects of Neural Networks with Domain Priors

no code implementations24 Nov 2021 Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian, Amit Sharma

A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output.


Sayer: Using Implicit Feedback to Optimize System Policies

no code implementations28 Oct 2021 Mathias Lécuyer, Sang Hoon Kim, Mihir Nanavati, Junchen Jiang, Siddhartha Sen, Amit Sharma, Aleksandrs Slivkins

We develop a methodology, called Sayer, that leverages implicit feedback to evaluate and train new system policies.

Data Augmentation

The Connection between Out-of-Distribution Generalization and Privacy of ML Models

1 code implementation7 Oct 2021 Divyat Mahajan, Shruti Tople, Amit Sharma

Through extensive evaluation on a synthetic dataset and image datasets like MNIST, Fashion-MNIST, and Chest X-rays, we show that a lower OOD generalization gap does not imply better robustness to MI attacks.

Domain Generalization Out-of-Distribution Generalization

DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions

1 code implementation27 Aug 2021 Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kiciman

Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.

Causal Discovery

Noise2Fast: Fast Self-Supervised Single Image Blind Denoising

1 code implementation23 Aug 2021 Jason Lequyer, Reuben Philip, Amit Sharma, Laurence Pelletier

Recent approaches have allowed for the denoising of single noisy images without access to any training data aside from that very image.

Image Denoising

On Cofibrations of Permutative categories

no code implementations24 Feb 2021 Amit Sharma

In this note we introduce a notion of free cofibrations of permutative categories.

Category Theory Algebraic Topology

The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective

no code implementations21 Dec 2020 Naman Goel, Alfonso Amayuelas, Amit Deshpande, Amit Sharma

For example, in multi-stage settings where decisions are made in multiple screening rounds, we use our framework to derive the minimal distributions required to design a fair algorithm.

Decision Making Fairness

Split-Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions

no code implementations11 Nov 2020 Yanbo Xu, Divyat Mahajan, Liz Manrao, Amit Sharma, Emre Kiciman

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 maximizing its benefits at minimum cost or potential harm.

Causal Inference Marketing

Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End

2 code implementations10 Nov 2020 Ramaravind Kommiya Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma

In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a model's prediction.

Causal Inference Counterfactual Explanation +1

DoWhy: An End-to-End Library for Causal Inference

4 code implementations9 Nov 2020 Amit Sharma, Emre Kiciman

In addition to efficient statistical estimators of a treatment's effect, successful application of causal inference requires specifying assumptions about the mechanisms underlying observed data and testing whether they are valid, and to what extent.

Causal Inference

Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals

no code implementations17 Sep 2020 Saloni Dash, Vineeth N Balasubramanian, Amit Sharma

We present a method for generating counterfactuals by incorporating a structural causal model (SCM) in an improved variant of Adversarially Learned Inference (ALI), that generates counterfactuals in accordance with the causal relationships between attributes of an image.

BIG-bench Machine Learning Fairness

Domain Generalization using Causal Matching

1 code implementation arXiv 2020 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.

Data Augmentation Domain Generalization +1

Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers

3 code implementations6 Dec 2019 Divyat Mahajan, Chenhao Tan, Amit Sharma

For explanations of ML models in critical domains such as healthcare and finance, counterfactual examples are useful for an end-user only to the extent that perturbation of feature inputs is feasible in the real world.

BIG-bench Machine Learning Decision Making

Alleviating Privacy Attacks via Causal Learning

1 code implementation ICML 2020 Shruti Tople, Amit Sharma, Aditya Nori

Such privacy risks are exacerbated when a model's predictions are used on an unseen data distribution.

Quantifying Infra-Marginality and Its Trade-off with Group Fairness

no code implementations3 Sep 2019 Arpita Biswas, Siddharth Barman, Amit Deshpande, Amit Sharma

To quantify this bias, we propose a general notion of $\eta$-infra-marginality that can be used to evaluate the extent of this bias.

Decision Making Fairness

Quantifying Error in the Presence of Confounders for Causal Inference

no code implementations10 Jul 2019 Rathin Desai, Amit Sharma

We show that many popular methods, including back-door methods can be considered as weighting or representation learning algorithms, and provide general error bounds for their causal estimates.

Causal Inference Representation Learning

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

7 code implementations19 May 2019 Ramaravind Kommiya Mothilal, Amit Sharma, Chenhao Tan

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions.

BIG-bench Machine Learning Point Processes

Learning to Prescribe Interventions for Tuberculosis Patients Using Digital Adherence Data

no code implementations5 Feb 2019 Jackson A. Killian, Bryan Wilder, Amit Sharma, Daksha Shah, Vinod Choudhary, Bistra Dilkina, Milind Tambe

Digital Adherence Technologies (DATs) are an increasingly popular method for verifying patient adherence to many medications.

Split-door criterion: Identification of causal effects through auxiliary outcomes

1 code implementation28 Nov 2016 Amit Sharma, Jake M. Hofman, Duncan J. Watts

We present a method for estimating causal effects in time series data when fine-grained information about the outcome of interest is available.

Recommendation Systems Time Series Analysis

Algorithms for Generating Ordered Solutions for Explicit AND/OR Structures

no code implementations23 Jan 2014 Priyankar Ghosh, Amit Sharma, P. P. Chakrabarti, Pallab Dasgupta

The proposed algorithms use a best first search technique and report the solutions using an implicit representation ordered by cost.

Service Composition

Cannot find the paper you are looking for? You can Submit a new open access paper.