default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJosif Grabocka
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c35]Sebastian Pineda-Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter, Josif Grabocka:
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How. ICLR 2024- [i37]Guri Zabërgja, Arlind Kadra, Josif Grabocka:
Tabular Data: Is Attention All You Need? CoRR abs/2402.03970 (2024) - [i36]Gresa Shala, André Biedenkapp, Josif Grabocka:
Hierarchical Transformers are Efficient Meta-Reinforcement Learners. CoRR abs/2402.06402 (2024) - [i35]Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley, Josif Grabocka, Frank Hutter:
Multi-objective Differentiable Neural Architecture Search. CoRR abs/2402.18213 (2024) - [i34]Sebastian Pineda-Arango, Maciej Janowski, Lennart Purucker, Arber Zela, Frank Hutter, Josif Grabocka:
Dynamic Post-Hoc Neural Ensemblers. CoRR abs/2410.04520 (2024) - [i33]Mihail Stoian, Alexander van Renen, Jan Kobiolka, Ping-Lin Kuo, Josif Grabocka, Andreas Kipf:
Lightweight Correlation-Aware Table Compression. CoRR abs/2410.14066 (2024) - [i32]Sebastian Pineda-Arango, Maciej Janowski, Lennart Purucker, Arber Zela, Frank Hutter, Josif Grabocka:
Ensembling Finetuned Language Models for Text Classification. CoRR abs/2410.19889 (2024) - [i31]Neeratyoy Mallik, Maciej Janowski, Johannes Hog, Herilalaina Rakotoarison, Aaron Klein, Josif Grabocka, Frank Hutter:
Warmstarting for Scaling Language Models. CoRR abs/2411.07340 (2024) - 2023
- [c34]Abdus Salam Khazi, Sebastian Pineda-Arango, Josif Grabocka:
Deep Ranking Ensembles for Hyperparameter Optimization. ICLR 2023 - [c33]Gresa Shala, André Biedenkapp, Frank Hutter, Josif Grabocka:
Gray-Box Gaussian Processes for Automated Reinforcement Learning. ICLR 2023 - [c32]Gresa Shala, Thomas Elsken, Frank Hutter, Josif Grabocka:
Transfer NAS with Meta-learned Bayesian Surrogates. ICLR 2023 - [c31]Sebastian Pineda-Arango
, Josif Grabocka:
Deep Pipeline Embeddings for AutoML. KDD 2023: 1907-1919 - [c30]Arlind Kadra, Maciej Janowski, Martin Wistuba, Josif Grabocka:
Scaling Laws for Hyperparameter Optimization. NeurIPS 2023 - [i30]Arlind Kadra, Maciej Janowski, Martin Wistuba, Josif Grabocka:
Deep Power Laws for Hyperparameter Optimization. CoRR abs/2302.00441 (2023) - [i29]Abdus Salam Khazi, Sebastian Pineda-Arango, Josif Grabocka:
Deep Ranking Ensembles for Hyperparameter Optimization. CoRR abs/2303.15212 (2023) - [i28]Mofassir ul Islam Arif, Mohsan Jameel, Josif Grabocka, Lars Schmidt-Thieme:
Phantom Embeddings: Using Embedding Space for Model Regularization in Deep Neural Networks. CoRR abs/2304.07262 (2023) - [i27]Arlind Kadra, Sebastian Pineda-Arango, Josif Grabocka:
Breaking the Paradox of Explainable Deep Learning. CoRR abs/2305.13072 (2023) - [i26]Sebastian Pineda-Arango, Josif Grabocka:
Deep Pipeline Embeddings for AutoML. CoRR abs/2305.14009 (2023) - [i25]Sebastian Pineda-Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter, Josif Grabocka:
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How. CoRR abs/2306.03828 (2023) - 2022
- [c29]Samuel Müller, Noah Hollmann, Sebastian Pineda-Arango, Josif Grabocka, Frank Hutter:
Transformers Can Do Bayesian Inference. ICLR 2022 - [c28]Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter:
Zero-shot AutoML with Pretrained Models. ICML 2022: 17138-17155 - [c27]Martin Wistuba, Arlind Kadra, Josif Grabocka:
Supervising the Multi-Fidelity Race of Hyperparameter Configurations. NeurIPS 2022 - [i24]Martin Wistuba, Arlind Kadra, Josif Grabocka:
Dynamic and Efficient Gray-Box Hyperparameter Optimization for Deep Learning. CoRR abs/2202.09774 (2022) - [i23]Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter:
Zero-Shot AutoML with Pretrained Models. CoRR abs/2206.08476 (2022) - 2021
- [j6]Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka:
Dataset2Vec: learning dataset meta-features. Data Min. Knowl. Discov. 35(3): 964-985 (2021) - [c26]Michael Ruchte, Josif Grabocka:
Scalable Pareto Front Approximation for Deep Multi-Objective Learning. ICDM 2021: 1306-1311 - [c25]Martin Wistuba, Josif Grabocka:
Few-Shot Bayesian Optimization with Deep Kernel Surrogates. ICLR 2021 - [c24]Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka:
Well-tuned Simple Nets Excel on Tabular Datasets. NeurIPS 2021: 23928-23941 - [c23]Sebastian Pineda-Arango, Hadi S. Jomaa, Martin Wistuba, Josif Grabocka:
HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML. NeurIPS Datasets and Benchmarks 2021 - [c22]Shayan Jawed, Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka:
Multi-task Learning Curve Forecasting Across Hyperparameter Configurations and Datasets. ECML/PKDD (1) 2021: 485-501 - [c21]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
A Guided Learning Approach for Item Recommendation via Surrogate Loss Learning. SIGIR 2021: 605-613 - [i22]Martin Wistuba, Josif Grabocka:
Few-Shot Bayesian Optimization with Deep Kernel Surrogates. CoRR abs/2101.07667 (2021) - [i21]Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka:
Hyperparameter Optimization with Differentiable Metafeatures. CoRR abs/2102.03776 (2021) - [i20]Michael Ruchte, Josif Grabocka:
Efficient Multi-Objective Optimization for Deep Learning. CoRR abs/2103.13392 (2021) - [i19]Sebastian Pineda-Arango, Hadi S. Jomaa, Martin Wistuba, Josif Grabocka:
HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML. CoRR abs/2106.06257 (2021) - [i18]Arlind Kadra, Marius Lindauer, Frank Hutter, Josif Grabocka:
Regularization is all you Need: Simple Neural Nets can Excel on Tabular Data. CoRR abs/2106.11189 (2021) - [i17]Michael Ruchte, Josif Grabocka:
Multi-task problems are not multi-objective. CoRR abs/2110.07301 (2021) - [i16]Samuel Müller, Noah Hollmann, Sebastian Pineda-Arango, Josif Grabocka, Frank Hutter:
Transformers Can Do Bayesian Inference. CoRR abs/2112.10510 (2021) - 2020
- [c20]Mofassir ul Islam Arif, Mohsan Jameel, Josif Grabocka, Lars Schmidt-Thieme:
Phantom Embeddings: Using Embeddings Space for Model Regularization in Deep Neural Networks. LWDA 2020: 47-58 - [c19]Shayan Jawed, Josif Grabocka, Lars Schmidt-Thieme:
Self-supervised Learning for Semi-supervised Time Series Classification. PAKDD (1) 2020: 499-511 - [c18]Rafael Rêgo Drumond, Lukas Brinkmeyer, Josif Grabocka, Lars Schmidt-Thieme:
HIDRA: Head Initialization across Dynamic targets for Robust Architectures. SDM 2020: 397-405
2010 – 2019
- 2019
- [c17]Vijaya Krishna Yalavarthi, Josif Grabocka, Hareesh Mandalapu, Lars Schmidt-Thieme:
Gait Verification using Deep Learning with a Pairwise Loss. BIOSIG 2019: 141-152 - [c16]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
Weighted Personalized Factorizations for Network Classification with Approximated Relation Weights. ICAART (Revised Selected Papers) 2019: 100-117 - [c15]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
Multi-Label Network Classification via Weighted Personalized Factorizations. ICAART (2) 2019: 357-366 - [c14]Hadi Samer Jomaa, Josif Grabocka, Lars Schmidt-Thieme, Alexander Borek:
A Hybrid Convolutional Approach for Parking Availability Prediction. IJCNN 2019: 1-8 - [c13]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
Multi-Relational Classification via Bayesian Ranked Non-Linear Embeddings. KDD 2019: 1132-1140 - [c12]Mohsan Jameel, Josif Grabocka, Mofassir ul Islam Arif, Lars Schmidt-Thieme:
Ring-Star: A Sparse Topology for Faster Model Averaging in Decentralized Parallel SGD. PKDD/ECML Workshops (1) 2019: 333-341 - [c11]Ahmed Rashed, Shayan Jawed, Jens Rehberg, Josif Grabocka, Lars Schmidt-Thieme, Andre Hintsches:
A Deep Multi-task Approach for Residual Value Forecasting. ECML/PKDD (3) 2019: 467-482 - [c10]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
Attribute-aware non-linear co-embeddings of graph features. RecSys 2019: 314-321 - [i15]Shayan Jawed, Eya Boumaiza, Josif Grabocka, Lars Schmidt-Thieme:
Data-Driven Vehicle Trajectory Forecasting. CoRR abs/1902.05400 (2019) - [i14]Ahmed Rashed, Josif Grabocka, Lars Schmidt-Thieme:
Multi-Label Network Classification via Weighted Personalized Factorizations. CoRR abs/1902.09294 (2019) - [i13]Josif Grabocka, Randolf Scholz, Lars Schmidt-Thieme:
Learning Surrogate Losses. CoRR abs/1905.10108 (2019) - [i12]Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme:
Dataset2Vec: Learning Dataset Meta-Features. CoRR abs/1905.11063 (2019) - [i11]Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme:
In Hindsight: A Smooth Reward for Steady Exploration. CoRR abs/1906.09781 (2019) - [i10]Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme:
Hyp-RL : Hyperparameter Optimization by Reinforcement Learning. CoRR abs/1906.11527 (2019) - [i9]Lukas Brinkmeyer, Rafael Rêgo Drumond, Randolf Scholz, Josif Grabocka, Lars Schmidt-Thieme:
Chameleon: Learning Model Initializations Across Tasks With Different Schemas. CoRR abs/1909.13576 (2019) - [i8]Rafael Rêgo Drumond, Lukas Brinkmeyer, Josif Grabocka, Lars Schmidt-Thieme:
HIDRA: Head Initialization across Dynamic targets for Robust Architectures. CoRR abs/1910.12749 (2019) - 2018
- [i7]Josif Grabocka, Lars Schmidt-Thieme:
NeuralWarp: Time-Series Similarity with Warping Networks. CoRR abs/1812.08306 (2018) - 2017
- [c9]Hanh T. H. Nguyen, Martin Wistuba, Josif Grabocka, Lucas Rêgo Drumond, Lars Schmidt-Thieme:
Personalized Deep Learning for Tag Recommendation. PAKDD (1) 2017: 186-197 - [i6]Dripta S. Raychaudhuri, Josif Grabocka, Lars Schmidt-Thieme:
Channel masking for multivariate time series shapelets. CoRR abs/1711.00812 (2017) - 2016
- [j5]Josif Grabocka, Martin Wistuba, Lars Schmidt-Thieme:
Fast classification of univariate and multivariate time series through shapelet discovery. Knowl. Inf. Syst. 49(2): 429-454 (2016) - [j4]Josif Grabocka, Nicolas Schilling, Lars Schmidt-Thieme:
Latent Time-Series Motifs. ACM Trans. Knowl. Discov. Data 11(1): 6:1-6:20 (2016) - [c8]Mit Shah, Josif Grabocka, Nicolas Schilling, Martin Wistuba, Lars Schmidt-Thieme:
Learning DTW-Shapelets for Time-Series Classification. CODS 2016: 3:1-3:8 - 2015
- [j3]Josif Grabocka, Martin Wistuba, Lars Schmidt-Thieme:
Scalable Classification of Repetitive Time Series Through Frequencies of Local Polynomials. IEEE Trans. Knowl. Data Eng. 27(6): 1683-1695 (2015) - [j2]Josif Grabocka, Lars Schmidt-Thieme:
Learning Through Non-linearly Supervised Dimensionality Reduction. Trans. Large Scale Data Knowl. Centered Syst. 17: 74-96 (2015) - [i5]Josif Grabocka, Martin Wistuba, Lars Schmidt-Thieme:
Scalable Discovery of Time-Series Shapelets. CoRR abs/1503.03238 (2015) - [i4]Martin Wistuba, Josif Grabocka, Lars Schmidt-Thieme:
Ultra-Fast Shapelets for Time Series Classification. CoRR abs/1503.05018 (2015) - [i3]Josif Grabocka, Nicolas Schilling, Lars Schmidt-Thieme:
Optimal Time-Series Motifs. CoRR abs/1505.00423 (2015) - 2014
- [j1]Josif Grabocka, Lars Schmidt-Thieme:
Invariant time-series factorization. Data Min. Knowl. Discov. 28(5-6): 1455-1479 (2014) - [c7]Josif Grabocka, Alexandros Dalkalitsis, Athanasios Lois, Evangelos Katsaros, Lars Schmidt-Thieme:
Realistic optimal policies for energy-efficient train driving. ITSC 2014: 629-634 - [c6]Josif Grabocka, Nicolas Schilling, Martin Wistuba, Lars Schmidt-Thieme:
Learning time-series shapelets. KDD 2014: 392-401 - [c5]Josif Grabocka, Erind Bedalli, Lars Schmidt-Thieme:
Supervised Nonlinear Factorizations Excel In Semi-supervised Regression. PAKDD (1) 2014: 188-199 - 2013
- [c4]Josif Grabocka, Lucas Drumond, Lars Schmidt-Thieme:
Supervised Dimensionality Reduction via Nonlinear Target Estimation. DaWaK 2013: 172-183 - [i2]Josif Grabocka, Martin Wistuba, Lars Schmidt-Thieme:
Time-Series Classification Through Histograms of Symbolic Polynomials. CoRR abs/1307.6365 (2013) - [i1]Josif Grabocka, Lars Schmidt-Thieme:
Invariant Factorization Of Time-Series. CoRR abs/1312.6712 (2013) - 2012
- [c3]Josif Grabocka, Alexandros Nanopoulos, Lars Schmidt-Thieme:
Classification of Sparse Time Series via Supervised Matrix Factorization. AAAI 2012: 929-934 - [c2]Josif Grabocka, Erind Bedalli, Lars Schmidt-Thieme:
Efficient Classification of Long Time-Series. ICT Innovations 2012: 47-57 - [c1]Josif Grabocka, Alexandros Nanopoulos, Lars Schmidt-Thieme:
Invariant Time-Series Classification. ECML/PKDD (2) 2012: 725-740
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-01-07 01:23 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
