Beyza Ermis

Publication Activity (10 Years)

Years Active: 2012-2024
Publications (10 Years): 27

Top Topics

Differentially Private

Tensor Factorization

Variational Inference

Top Venues

Publications

Çagatay Yildiz, Nishaanth Kanna Ravichandran, Prishruit Punia, Matthias Bethge, Beyza Ermis
Investigating Continual Pretraining in Large Language Models: Insights and Implications. CoRR (2024)
Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm. CoRR (2024)
Luiza Pozzobon, Patrick Lewis, Sara Hooker, Beyza Ermis
From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models. CoRR (2024)
Beyza Ermis, Luiza Pozzobon, Sara Hooker, Patrick Lewis
From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models. ACL (Findings) (2024)
Ted Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermis, Acyr Locatelli, Sara Hooker
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning. ICLR (2024)
Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker
Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models. EMNLP (Findings) (2023)
Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker
On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research. CoRR (2023)
Meriem Boubdir, Edward Kim, Beyza Ermis, Sara Hooker, Marzieh Fadaee
Elo Uncovered: Robustness and Best Practices in Language Model Evaluation. CoRR (2023)
Ted Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermis, Acyr Locatelli, Sara Hooker
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning. CoRR (2023)
Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker
On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research. EMNLP (2023)
Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker
Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models. CoRR (2023)
Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
PASHA: Efficient HPO and NAS with Progressive Resource Allocation. ICLR (2023)
Meriem Boubdir, Edward Kim, Beyza Ermis, Marzieh Fadaee, Sara Hooker
Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation. CoRR (2023)
Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, Cédric Archambeau
Continual Learning with Transformers for Image Classification. CoRR (2022)
Beyza Ermis, Giovanni Zappella, Martin Wistuba, Cédric Archambeau
Memory Efficient Continual Learning for Neural Text Classification. CoRR (2022)
Ondrej Bohdal, Lukas Balles, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
PASHA: Efficient HPO with Progressive Resource Allocation. CoRR (2022)
Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, Cédric Archambeau
Continual Learning with Transformers for Image Classification. CVPR Workshops (2022)
Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, Cédric Archambeau
Memory Efficient Continual Learning with Transformers. NeurIPS (2022)
Beyza Ermis, Giovanni Zappella, Cédric Archambeau
Towards robust episodic meta-learning. UAI (2021)
Beyza Ermis, Patrick Ernst, Yannik Stein, Giovanni Zappella
Learning to Rank in the Position Based Model with Bandit Feedback. CoRR (2020)
Beyza Ermis, A. Taylan Cemgil
Data Sharing via Differentially Private Coupled Matrix Factorization. ACM Trans. Knowl. Discov. Data 14 (3) (2020)
Claire Vernade, Alexandra Carpentier, Tor Lattimore, Giovanni Zappella, Beyza Ermis, Michael Brückner
Linear bandits with Stochastic Delayed Feedback. ICML (2020)
Beyza Ermis, Patrick Ernst, Yannik Stein, Giovanni Zappella
Learning to Rank in the Position Based Model with Bandit Feedback. CIKM (2020)
Sinan Yildirim, Beyza Ermis
Exact MCMC with differentially private moves - Revisiting the penalty algorithm in a data privacy framework. Stat. Comput. 29 (5) (2019)
Claire Vernade, Alexandra Carpentier, Giovanni Zappella, Beyza Ermis, Michael Brückner
Contextual Bandits under Delayed Feedback. CoRR (2018)
Beyza Ermis, Ali Taylan Cemgil
Differentially Private Dropout. CoRR (2017)
Beyza Ermis, Ali Taylan Cemgil
Differentially Private Variational Dropout. CoRR (2017)
Beyza Ermis, Evrim Acar, Ali Taylan Cemgil
Link prediction in heterogeneous data via generalized coupled tensor factorization. Data Min. Knowl. Discov. 29 (1) (2015)
Umut Simsekli, Ali Taylan Cemgil, Beyza Ermis
Learning mixed divergences in coupled matrix and tensor factorization models. ICASSP (2015)
Beyza Ermis, Yusuf Kenan Yilmaz, Ali Taylan Cemgil, Evrim Acar
Variational Inference For Probabilistic Latent Tensor Factorization with KL Divergence. CoRR (2014)
Beyza Ermis, Ali Taylan Cemgil
A Bayesian Tensor Factorization Model via Variational Inference for Link Prediction. CoRR (2014)
Beyza Ermis, Ali Taylan Cemgil, Neda Barzegar Marvasti, Burak Acar
Liver CT Annotation via Generalized Coupled Tensor Factorization. CLEF (Working Notes) (2014)
Beyza Ermis, Guillaume Bouchard
Iterative Splits of Quadratic Bounds for Scalable Binary Tensor Factorization. UAI (2014)
Umut Simsekli, Beyza Ermis, A. Taylan Cemgil, Evrim Acar
Optimal weight learning for Coupled Tensor Factorization with mixed divergences. EUSIPCO (2013)
Beyza Ermis, Ali Taylan Cemgil, Evrim Acar
Generalized coupled symmetric tensor factorization for link prediction. SIU (2013)
Beyza Ermis, Evrim Acar, A. Taylan Cemgil
Link Prediction via Generalized Coupled Tensor Factorisation CoRR (2012)