Publications (41)
Local Saddle Point Optimization: A Curvature Exploitation Approach
Leonard Adolphs, Hadi Daneshmand, Aurelien Lucchi +1
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann
Learning and Evaluating Sparse Interpretable Sentence Embeddings
Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko +1
Variance Reduced Stochastic Gradient Descent with Neighbors
Thomas Hofmann, Aurelien Lucchi, Simon Lacoste-Julien +1
Probabilistic Latent Semantic Analysis
Thomas Hofmann
Chemical and Crystallographic Characterization of the Tip Apex in Scanning Probe Microscopy
Thomas Hofmann, Florian Pielmeier, Franz J. Giessibl
Hyperbolic Neural Networks
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Kevin Roth, Yannic Kilcher, Thomas Hofmann
Kernel methods in machine learning
Thomas Hofmann, Bernhard Schölkopf, Alexander J. Smola
Starting Small -- Learning with Adaptive Sample Sizes
Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann
Semantic Interpolation in Implicit Models
Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann
The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
Yannic Kilcher, Thomas Hofmann
Preparation of light-atom tips for Scanning Probe Microscopy by explosive delamination
Thomas Hofmann, Joachim Welker, Franz J. Giessibl
Controlling a d-level atom in a cavity
Thomas Hofmann, Michael Keyl
Generator Reversal
Yannic Kilcher, Aurélien Lucchi, Thomas Hofmann
Zero-Shot Dual Machine Translation
Lierni Sestorain, Massimiliano Ciaramita, Christian Buck +1
Learning Aerial Image Segmentation from Online Maps
Pascal Kaiser, Jan Dirk Wegner, Aurelien Lucchi +3
Deep Joint Entity Disambiguation with Local Neural Attention
Octavian-Eugen Ganea, Thomas Hofmann
A Semi-supervised Framework for Image Captioning
Wenhu Chen, Aurelien Lucchi, Thomas Hofmann
Fully Character-Level Neural Machine Translation without Explicit Segmentation
Jason Lee, Kyunghyun Cho, Thomas Hofmann
Cosmological constraints from noisy convergence maps through deep learning
Janis Fluri, Tomasz Kacprzak, Aurelien Lucchi +3
Probabilistic Bag-Of-Hyperlinks Model for Entity Linking
Octavian-Eugen Ganea, Marina Ganea, Aurelien Lucchi +2
A Variance Reduced Stochastic Newton Method
Aurelien Lucchi, Brian McWilliams, Thomas Hofmann
Communication-Efficient Distributed Dual Coordinate Ascent
Martin Jaggi, Virginia Smith, Martin TakÃ¡Ä +4
Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization
Jonas Kohler, Hadi Daneshmand, Aurelien Lucchi +3
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification
Jan Deriu, Aurelien Lucchi, Valeria De Luca +5
Adversarially Robust Training through Structured Gradient Regularization
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin +1
Exponential Families for Conditional Random Fields
Yasemin Altun, Alex Smola, Thomas Hofmann
End-to-End Neural Entity Linking
Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann
Accelerated Dual Learning by Homotopic Initialization
Hadi Daneshmand, Hamed Hassani, Thomas Hofmann
DynaNewton - Accelerating Newton's Method for Machine Learning
Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann
An Online Learning Approach to Generative Adversarial Networks
Paulina Grnarova, Kfir Y. Levy, Aurelien Lucchi +2
Flexible Prior Distributions for Deep Generative Models
Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann
Fast cosmic web simulations with generative adversarial networks
Andres C. Rodriguez, Tomasz Kacprzak, Aurelien Lucchi +5
A Distributed Second-Order Algorithm You Can Trust
Celestine Dünner, Aurelien Lucchi, Matilde Gargiani +3
Deep State Space Models for Unconditional Word Generation
Florian Schmidt, Thomas Hofmann
Parametrizing filters of a CNN with a GAN
Yannic Kilcher, Gary Becigneul, Thomas Hofmann
Escaping Saddles with Stochastic Gradients
Hadi Daneshmand, Jonas Kohler, Aurelien Lucchi +1
Stabilizing Training of Generative Adversarial Networks through Regularization
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin +1
Cosmological model discrimination with Deep Learning
Jorit Schmelzle, Aurelien Lucchi, Tomasz Kacprzak +4
Semantic Place Descriptors for Classification and Map Discovery
Siddharth Sarda, Carsten Eickhoff, Thomas Hofmann