◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Hartmut Maennel

Google Research

8 papers hereh-index 7582 citations13 works total

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

author position
  • sole author1
  • first author2
  • middle author5

Across the 8 of 8 papers where every author was matched, so the position is known.

fields
  • cs.LG4
  • stat.ML3
  • physics.chem-ph1
affiliations
  • Google Research

identity via Semantic Scholar / OpenAlex

activity
20182022
most citedDeep Learning Through the Lens of Example Difficulty

20 citations · 44 across the 4 of their papers we have counts for

collaborators
Showing stat.MLShow all

3 papers · 1 filter

stat.ML2020

What Do Neural Networks Learn When Trained With Random Labels?

Hartmut Maennel, Ibrahim Alabdulmohsin, Ilya Tolstikhin +4

We study deep neural networks (DNNs) trained on natural image data with entirely random labels. Despite its popularity in the literature, where it is often used to study memorizati…

stat.ML2020

Exact marginal inference in Latent Dirichlet Allocation

Hartmut Maennel

Assume we have potential "causes" z∈Z, which produce "events" w with known probabilities β(w∣z). We observe w1​,w2​,...,wn​, what can we say about the distribution of th…

stat.ML2018

Gradient Descent Quantizes ReLU Network Features

Hartmut Maennel, Olivier Bousquet, Sylvain Gelly

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solut…

◍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.