270 citations · 669 across the 40 of their papers we have counts for
25 papers · 1 filter
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
Isha Puri, Amit Dhurandhar, Tejaswini Pedapati +3
In recent years there has been a considerable amount of research on local post hoc explanations for neural networks. However, work on building interpretable neural architectures ha…
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Dennis Wei, Rahul Nair, Amit Dhurandhar +3
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interp…
Anomaly Attribution with Likelihood Compensation
Tsuyoshi Idé, Amit Dhurandhar, Jiří Navrátil +2
This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption…
Auto-Transfer: Learning to Route Transferrable Representations
Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss +3
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be diffic…
Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners
Karthikeyan Natesan Ramamurthy, Amit Dhurandhar, Dennis Wei +1
Post-hoc explanations for black box models have been studied extensively in classification and regression settings. However, explanations for models that output similarity between…
Local Explanations for Reinforcement Learning
Ronny Luss, Amit Dhurandhar, Miao Liu
Many works in explainable AI have focused on explaining black-box classification models. Explaining deep reinforcement learning (RL) policies in a manner that could be understood b…
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…
AI Explainability 360: Impact and Design
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen +17
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.…
Multihop: Leveraging Complex Models to Learn Accurate Simple Models
Amit Dhurandhar, Tejaswini Pedapati
Knowledge transfer from a complex high performing model to a simpler and potentially low performing one in order to enhance its performance has been of great interest over the last…
When Stability meets Sufficiency: Informative Explanations that do not Overwhelm
Ronny Luss, Amit Dhurandhar
Recent studies evaluating various criteria for explainable artificial intelligence (XAI) suggest that fidelity, stability, and comprehensibility are among the most important metric…
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…
Invariant Risk Minimization Games
Kartik Ahuja, Karthikeyan Shanmugam, Kush R. Varshney +1
The standard risk minimization paradigm of machine learning is brittle when operating in environments whose test distributions are different from the training distribution due to s…
Model Agnostic Multilevel Explanations
Karthikeyan Natesan Ramamurthy, Bhanukiran Vinzamuri, Yunfeng Zhang +1
In recent years, post-hoc local instance-level and global dataset-level explainability of black-box models has received a lot of attention. Much less attention has been given to ob…
Learning Global Transparent Models Consistent with Local Contrastive Explanations
Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam +1
There is a rich and growing literature on producing local contrastive/counterfactual explanations for black-box models (e.g. neural networks). In these methods, for an input, an ex…
Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy +5
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility f…
Model Agnostic Contrastive Explanations for Structured Data
Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan +3
Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this…
Enhancing Simple Models by Exploiting What They Already Know
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss
There has been recent interest in improving performance of simple models for multiple reasons such as interpretability, robust learning from small data, deployment in memory constr…
Leveraging Latent Features for Local Explanations
Ronny Luss, Pin-Yu Chen, Amit Dhurandhar +4
As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions…
Streaming Methods for Restricted Strongly Convex Functions with Applications to Prototype Selection
Karthik S. Gurumoorthy, Amit Dhurandhar
In this paper, we show that if the optimization function is restricted-strongly-convex (RSC) and restricted-smooth (RSM) -- a rich subclass of weakly submodular functions -- then a…
Improving Simple Models with Confidence Profiles
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss +1
In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretabl…
Learning with Changing Features
Amit Dhurandhar, Steve Hanneke, Liu Yang
In this paper we study the setting where features are added or change interpretation over time, which has applications in multiple domains such as retail, manufacturing, finance. I…