Search Results - "Wistuba, Martin"

Scalable Gaussian process-based transfer surrogates for hyperparameter optimization by Wistuba, Martin, Schilling, Nicolas, Schmidt-Thieme, Lars

“…Algorithm selection as well as hyperparameter optimization are tedious task that have to be dealt with when applying machine learning to real-world problems…”
Get full text

Fast classification of univariate and multivariate time series through shapelet discovery by Grabocka, Josif, Wistuba, Martin, Schmidt-Thieme, Lars

“…Time-series classification is an important problem for the data mining community due to the wide range of application domains involving time-series data. A…”
Get full text

Scalable Classification of Repetitive Time Series Through Frequencies of Local Polynomials by Grabocka, Josif, Wistuba, Martin, Schmidt-Thieme, Lars

“…Time-series classification has attracted considerable research attention due to the various domains where time-series data are observed, ranging from medicine…”
Get full text

Automated Data Science for Relational Data by Lam, Hoang Thanh, Buesser, Beat, Min, Hong, Minh, Tran Ngoc, Wistuba, Martin, Khurana, Udayan, Bramble, Gregory, Salonidis, Theodoros, Wang, Dakuo, Samulowitz, Horst

“…Feature engineering is a crucial but tedious task that requires up to 80% of the total time in data science projects. A significant challenge is when data…”
Get full text

Practical Deep Learning Architecture Optimization by Wistuba, Martin

“…The design of neural network architectures for a new data set is a laborious task which requires human deep learning expertise. In order to make deep learning…”
Get full text

Sequential Model-Free Hyperparameter Tuning by Wistuba, Martin, Schilling, Nicolas, Schmidt-Thieme, Lars

“…Hyperparameter tuning is often done manually but current research has proven that automatic tuning yields effective hyperparameter configurations even faster…”
Get full text

XferNAS: Transfer Neural Architecture Search by Wistuba, Martin

“…The term Neural Architecture Search (NAS) refers to the automatic optimization of network architectures for a new, previously unknown task. Since testing an…”
Get full text

Learning hyperparameter optimization initializations by Wistuba, Martin, Schilling, Nicolas, Schmidt-Thieme, Lars

“…Hyperparameter optimization is often done manually or by using a grid search. However, recent research has shown that automatic optimization techniques are…”
Get full text

Finding Competitive Network Architectures Within a Day Using UCT by Wistuba, Martin

“…Proceedings of the 5th IEEE International Conference on Data Science and Advanced Analytics, pages 263-272, 2018 The design of neural network architectures for…”
Get full text

Few-Shot Bayesian Optimization with Deep Kernel Surrogates by Wistuba, Martin, Grabocka, Josif

“…Hyperparameter optimization (HPO) is a central pillar in the automation of machine learning solutions and is mainly performed via Bayesian optimization, where…”
Get full text

Learning to Rank Learning Curves by Wistuba, Martin, Pedapati, Tejaswini

“…Many automated machine learning methods, such as those for hyperparameter and neural architecture optimization, are computationally expensive because they…”
Get full text

Continual Learning with Transformers for Image Classification by Ermis, Beyza, Zappella, Giovanni, Wistuba, Martin, Rawal, Aditya, Archambeau, Cedric

“…In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn…”
Get full text

Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need by Wistuba, Martin, Sivaprasad, Prabhu Teja, Balles, Lukas, Zappella, Giovanni

“…Recent Continual Learning (CL) methods have combined pretrained Transformers with prompt tuning, a parameter-efficient fine-tuning (PEFT) technique. We argue…”
Get full text

Inductive Transfer for Neural Architecture Optimization by Wistuba, Martin, Pedapati, Tejaswini

“…The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures…”
Get full text

Continual Learning with Low Rank Adaptation by Wistuba, Martin, Sivaprasad, Prabhu Teja, Balles, Lukas, Zappella, Giovanni

“…Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they…”
Get full text

Supervising the Multi-Fidelity Race of Hyperparameter Configurations by Wistuba, Martin, Kadra, Arlind, Grabocka, Josif

“…Multi-fidelity (gray-box) hyperparameter optimization techniques (HPO) have recently emerged as a promising direction for tuning Deep Learning methods…”
Get full text

Renate: A Library for Real-World Continual Learning by Wistuba, Martin, Ferianc, Martin, Balles, Lukas, Archambeau, Cedric, Zappella, Giovanni

“…Continual learning enables the incremental training of machine learning models on non-stationary data streams.While academic interest in the topic is high,…”
Get full text

Scalable Multi-Class Bayesian Support Vector Machines for Structured and Unstructured Data by Wistuba, Martin, Rawat, Ambrish

“…We introduce a new Bayesian multi-class support vector machine by formulating a pseudo-likelihood for a multi-class hinge loss in the form of a location-scale…”
Get full text

Variational Boosted Soft Trees by Cinquin, Tristan, Rukat, Tammo, Schmidt, Philipp, Wistuba, Martin, Bekasov, Artur

“…Gradient boosting machines (GBMs) based on decision trees consistently demonstrate state-of-the-art results on regression and classification tasks with tabular…”
Get full text

Scaling Laws for Hyperparameter Optimization by Kadra, Arlind, Janowski, Maciej, Wistuba, Martin, Grabocka, Josif

“…Hyperparameter optimization is an important subfield of machine learning that focuses on tuning the hyperparameters of a chosen algorithm to achieve peak…”
Get full text