Beyza Ermis

According to our database, Beyza Ermis authored at least 34 papers between 2012 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning.

Aakanksha, Arash Ahmadian, Seraphina Goldfarb-Tarrant, Beyza Ermis, Marzieh Fadaee, Sara Hooker

CoRR, 2024

Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress.

Ayomide Odumakinde, Daniel D'souza, Pat Verga, Beyza Ermis, Sara Hooker

CoRR, 2024

Investigating Continual Pretraining in Large Language Models: Insights and Implications.

Çagatay Yildiz, Nishaanth Kanna Ravichandran, Prishruit Punia, Matthias Bethge, Beyza Ermis

CoRR, 2024

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning.

Ted Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermis, Acyr Locatelli, Sara Hooker

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?

Firat Öncel, Matthias Bethge, Beyza Ermis, Mirco Ravanelli, Cem Subakan, Çagatay Yildiz

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm.

Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models.

Beyza Ermis, Luiza Pozzobon, Sara Hooker, Patrick Lewis

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Elo Uncovered: Robustness and Best Practices in Language Model Evaluation.

Meriem Boubdir, Edward Kim, Beyza Ermis, Sara Hooker, Marzieh Fadaee

CoRR, 2023

Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation.

Meriem Boubdir, Edward Kim, Beyza Ermis, Marzieh Fadaee, Sara Hooker

CoRR, 2023

PASHA: Efficient HPO and NAS with Progressive Resource Allocation.

Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models.

Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research.

Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

PASHA: Efficient HPO with Progressive Resource Allocation.

Ondrej Bohdal, Lukas Balles, Beyza Ermis, Cédric Archambeau, Giovanni Zappella

CoRR, 2022

Memory Efficient Continual Learning for Neural Text Classification.

Beyza Ermis, Giovanni Zappella, Martin Wistuba, Cédric Archambeau

CoRR, 2022

Memory Efficient Continual Learning with Transformers.

Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, Cédric Archambeau

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Continual Learning with Transformers for Image Classification.

Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, Cédric Archambeau

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

2021

Towards robust episodic meta-learning.

Beyza Ermis, Giovanni Zappella, Cédric Archambeau

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

2020

Bayesian approaches for privacy preserving data sharing (Mahremiyeti koruyan veri paylaşımında bayesçi yöntemler)

Beyza Ermis

PhD thesis, 2020

Data Sharing via Differentially Private Coupled Matrix Factorization.

Beyza Ermis, A. Taylan Cemgil

ACM Trans. Knowl. Discov. Data, 2020

Linear bandits with Stochastic Delayed Feedback.

Claire Vernade, Alexandra Carpentier, Tor Lattimore, Giovanni Zappella, Beyza Ermis, Michael Brückner

Proceedings of the 37th International Conference on Machine Learning, 2020

Learning to Rank in the Position Based Model with Bandit Feedback.

Beyza Ermis, Patrick Ernst, Yannik Stein, Giovanni Zappella

Proceedings of the CIKM '20: The 29th ACM International Conference on Information and Knowledge Management, 2020

2019

Exact MCMC with differentially private moves - Revisiting the penalty algorithm in a data privacy framework.

Sinan Yildirim, Beyza Ermis

Stat. Comput., 2019

2018

Contextual Bandits under Delayed Feedback.

Claire Vernade, Alexandra Carpentier, Giovanni Zappella, Beyza Ermis, Michael Brückner

CoRR, 2018

2017

Differentially Private Variational Dropout.

Beyza Ermis, Ali Taylan Cemgil

CoRR, 2017

Differentially Private Dropout.

Beyza Ermis, Ali Taylan Cemgil

CoRR, 2017

2015

Link prediction in heterogeneous data via generalized coupled tensor factorization.

Beyza Ermis, Evrim Acar, Ali Taylan Cemgil

Data Min. Knowl. Discov., 2015

Learning mixed divergences in coupled matrix and tensor factorization models.

Umut Simsekli, Ali Taylan Cemgil, Beyza Ermis

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Variational Inference For Probabilistic Latent Tensor Factorization with KL Divergence.

Beyza Ermis, Yusuf Kenan Yilmaz, Ali Taylan Cemgil, Evrim Acar

CoRR, 2014

A Bayesian Tensor Factorization Model via Variational Inference for Link Prediction.

Beyza Ermis, Ali Taylan Cemgil

CoRR, 2014

Iterative Splits of Quadratic Bounds for Scalable Binary Tensor Factorization.

Beyza Ermis, Guillaume Bouchard

Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence, 2014

Liver CT Annotation via Generalized Coupled Tensor Factorization.

Beyza Ermis, Ali Taylan Cemgil, Neda Barzegar Marvasti, Burak Acar

Proceedings of the Working Notes for CLEF 2014 Conference, 2014

2013

Generalized coupled symmetric tensor factorization for link prediction.

Beyza Ermis, Ali Taylan Cemgil, Evrim Acar

Proceedings of the 21st Signal Processing and Communications Applications Conference, 2013

Optimal weight learning for Coupled Tensor Factorization with mixed divergences.

Umut Simsekli, Beyza Ermis, A. Taylan Cemgil, Evrim Acar

Proceedings of the 21st European Signal Processing Conference, 2013

2012

Link Prediction via Generalized Coupled Tensor Factorisation

Beyza Ermis, Evrim Acar, A. Taylan Cemgil

CoRR, 2012