◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

D. Erhan

14 papers hereh-index 37130.8k citations60 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author10
  • last author3

Across the 13 of 14 papers where every author was matched, so the position is known.

fields
  • cs.CV7
  • cs.LG3
  • cs.RO1
  • cs.SC1
  • stat.ME1
  • stat.ML1

identity via Semantic Scholar / OpenAlex

activity
20122023
most citedThe (Un)reliability of saliency methods

165 citations · 439 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

3 papers · 1 filter

cs.LG2020★ 4 cited

Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning

Mohammad Babaeizadeh, Mohammad Taghi Saffar, Danijar Hafner +4

Model-based reinforcement learning (MBRL) methods have shown strong sample efficiency and performance across a variety of tasks, including when faced with high-dimensional visual o…

cs.LG2018

A Benchmark for Interpretability Methods in Deep Neural Networks

Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans +1

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification dat…

cs.LG2012★ 3 cited

Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits

Miroslav Dudik, Dumitru Erhan, John Langford +1

We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.