Haris Vikalo

Haris Vikalo Department of Electrical and Computer Engineering The University of Texas at Austin 1 University Station C0803 Austin, TX 78712-0240 Email: hvikalo@ece.utexas.edu Phone: + 1 512 232 7922 Office hours (Fall 2024): Tue, Thu 2-3pm

Research

My research is in the broad area of signal processing and machine learning, with applications to bioinformatics, communications and distributed systems. Recent publications:

• H. Chen and H. Vikalo, "Heterogeneity-guided client sampling: Towards fast and efficient non-IID federated learning," Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada, December 10-15, 2024.
  
• H. Chen and H. Vikalo, "Recovering labels from local updates in federated learning," Proceedings of the Forty-first International Conference on Machine Learning (ICML), Vienna, Austria, July 22-26, 2024.
  
• H. B. Beytur, A. Aydin, G. de Veciana and H. Vikalo, "Optimization of offloading policies for accuracy-delay tradeoffs in hierarchical inference," IEEE International Conference on Computer Communications (INFOCOM ’24), Vancouver, BC, Canada, May 20-23, 2024.
  
• Y. Chen, C. Wang and H. Vikalo, "Fed-QSSL: A framework for personalized federated learning under bitwidth and data heterogeneity," 38th AAAI Conference on Artificial Intelligence (AAAI ’24), Vancouver, BC, Canada, February 20-27, 2024.
  
• S. Consul, Z. Ke and H. Vikalo, "XHap: Haplotype assembly using long-distance read correlations learned by transformers," Bioinformatics Advances, vol. 3, no. 1, 2023, pp. 1-11.
  
  

  The complete list: Journal and conference papers.