I’m a final-year PhD student in Electrical Engineering and Computer Sciences at UC Berkeley. My advisors are Moritz Hardt and Michael Jordan, and I am affiliated with the Berkeley AI Research group. I am broadly interested in theoretical machine learning and statistics.

I spent the summer of 2020 interning at Apple AI Research, hosted by Vitaly Feldman. My research is generously supported by an Apple PhD Fellowship in AI/ML.

I completed my BEng in Electrical and Computer Engineering at the University of Novi Sad in Serbia, with a focus on communications and signal processing. My undergraduate advisor was Dragana Bajovic. In undergrad I spent a summer at Caltech, working with Babak Hassibi.

Contact

email: “firstname”@eecs.berkeley.edu or “firstname”.“lastname”@berkeley.edu
office: 537 Soda Hall

Publications and preprints

(* denotes equal contribution, α-β denotes alphabetical ordering)

Algorithmic Collective Action in Machine Learning
(α-β) M. Hardt, E. Mazumdar, C. Mendler-Dünner, T. Zrnic
International Conference on Machine Learning (ICML) 2023 arxiv talk

Prediction-Powered Inference
(α-β) A. N. Angelopoulos, S. Bates, C. Fannjiang, M. I. Jordan, T. Zrnic
Preprint arxiv code

Locally Simultaneous Inference
T. Zrnic, W. Fithian
Preprint arxiv talk
Presented at the International Conference on Multiple Comparisons Procedures (MCP) 2022

Valid Inference after Causal Discovery
P. Gradu*, T. Zrnic*, Y. Wang, M. I. Jordan
Preprint arxiv

A Note on Zeroth-Order Optimization on the Simplex
T. Zrnic, E. Mazumdar
Note arxiv

Regret Minimization with Performative Feedback
M. Jagadeesan, T. Zrnic, C. Mendler-Dünner
International Conference on Machine Learning (ICML) 2022 ICML arxiv
Presented at the Symposium on Foundations of Responsible Computing (FORC) 2022

Post-Selection Inference via Algorithmic Stability
T. Zrnic, M. I. Jordan
Under minor revision at the Annals of Statistics (AoS) arxiv talk

Private Prediction Sets
A. N. Angelopoulos*, S. Bates*, T. Zrnic*, M. I. Jordan
Harvard Data Science Review (HDSR) 2022 HDSR arxiv code

Who Leads and Who Follows in Strategic Classification?
T. Zrnic*, E. Mazumdar*, S. S. Sastry, M. I. Jordan
Conference on Neural Information Processing Systems (NeurIPS) 2021 NeurIPS arxiv

Individual Privacy Accounting via a Rényi Filter
(α-β) V. Feldman, T. Zrnic
Conference on Neural Information Processing Systems (NeurIPS) 2021 NeurIPS arxiv short talk long talk
Presented at the Symposium on Foundations of Responsible Computing (FORC) 2021

Outside the Echo Chamber: Optimizing the Performative Risk
J. Miller*, J. C. Perdomo*, T. Zrnic*
International Conference on Machine Learning (ICML) 2021 ICML arxiv blog post
Presented at the Symposium on Foundations of Responsible Computing (FORC) 2021

Asynchronous Online Testing of Multiple Hypotheses
T. Zrnic, A. Ramdas, M. I. Jordan
Journal of Machine Learning Research (JMLR) 2021 JMLR arxiv blog post code online FDR package
Presented at the International Conference on Multiple Comparisons Procedures (MCP) 2019

Stochastic Optimization for Performative Prediction
C. Mendler-Dünner*, J. C. Perdomo*, T. Zrnic*, M. Hardt
Conference on Neural Information Processing Systems (NeurIPS) 2020 NeurIPS arxiv blog post code

Performative Prediction
J. C. Perdomo*, T. Zrnic*, C. Mendler-Dünner, M. Hardt
International Conference on Machine Learning (ICML) 2020 ICML arxiv blog post talk code

The Power of Batching in Multiple Hypothesis Testing
T. Zrnic, D. L. Jiang, A. Ramdas, M. I. Jordan
International Conference on Artificial Intelligence and Statistics (AISTATS) 2020 AISTATS arxiv talk code

Natural Analysts in Adaptive Data Analysis
T. Zrnic, M. Hardt
International Conference on Machine Learning (ICML) 2019 ICML arxiv talk

SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
A. Ramdas, T. Zrnic, M. J. Wainwright, M. I. Jordan
International Conference on Machine Learning (ICML) 2018 ICML arxiv code

Tensor-Based Crowdsourced Clustering via Triangle Queries
R. K. Vinayak, T. Zrnic, B. Hassibi
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2017 IEEE

Improving Location of Recording Classification Using Electric Network Frequency (ENF) Analysis
Z. Saric, A. Zunic, T. Zrnic, M. Knezevic, D. Despotovic, T. Delic
IEEE International Symposium on Intelligent Systems and Informatics (SISY) 2016 IEEE

Other

People often ask me how to pronounce my name. A good option is Tijana = tee-yah-na, Zrnic = zer-nitch.