Prof. Ofer Shir

Prof. Ofer Shir
Associate Professor of Computer Science
Principal Investigator
Research Group Leader
PhD
Phone
972-4-7700527

Lab Website

Research Interests:

Computational Intelligence, Experimental Optimization, Statistical Learning, Theory of Randomized Search Heuristics, Quantum ML

Quote
You are the outcome of 3.8 billion years of evolutionary success. Act like it.

The advent of modern laboratory and field experiments, as well as of computerized systems, enables researchers to control experiments and analyze their big-data in high-speed rates. Yet, algorithmic design of intelligent experiments for optimization and learning of prescribed objectives may constitute the next level. Very little is known today about the general usefulness of optimization heuristics and statistical learning methods in laboratory experiments, about their strengths and weaknesses when compared to traditional Design-of-Experiments approaches, or about any kind of guidelines which approach to prefer, depending upon the dimensionality of the search-space, the levels of uncertainty and the number of available trials.

We are interested in learning and optimization questions related to systems within the Natural Sciences. In particular, Operational Research and Machine Learning aspects of experimental domains, that is, practical physical- and life-sciences problems whose computerized models are unavailable or too expensive to be executed, and thus necessitate real-world experiments toward the end of their global optimization.
We have specific interest in the realms of Chemistry and Bio-Molecules' Production; Our targeted family of methodologies stem from Computational Intelligence, and especially Natural Computing.

Our current activities include Experimental Combinatorial Optimization (with Dr. Noy), Benchmarking Randomized Search Heuristics (with Prof. Bäck and Dr. Doerr), Geo-Statistical Learning (with Prof. Litaor), Effective Detection of Foliage Diseases in Vineyards (with Dr. Sharon), and Deep Learning of a Complementary Ensemble of Sporadic Input Maps (with Prof. Linker and Dr. Chen).

CV

Education

2008-2010 Postdoctoral Research Associate, Princeton University, USA
2008 Ph.D., Computer Science, Leiden University, The Netherlands
2004 M.Sc., Computer Science, Leiden University, The Netherlands
2003 B.Sc., Physics and Computer Science, The Hebrew University of Jerusalem, Israel

Academic and research positions

2020- Associate Professor, Computer Science Department, Tel-Hai College
2019- Head, Computer Science Department, Tel-Hai College
2013- Principal Investigator, MIGAL-Galilee Research Institute

Previously

2012-2020 Lecturer and Senior Lecturer, Computer Science Department, Tel-Hai College
2010-2013, Research Staff Member, IBM-Research

Funding
  1. [M.O.S.T.] Deep Learning of a Complementary Ensemble of Sporadic Input Maps (with Prof. Linker/Technion-IIT and Dr. Chen/Migal)
  2. [M.O.S.T.] Experimental Combinatorial Optimization of Post-harvesting Protocols (Postdoctoral Fellowship: Dr. Boris Yazmir)
  3. [BARD] Precision agriculture: geo-statistical learning (with Prof. Litaor/Migal)
  4. [M.O.A.G.] Effective Detection of Foliage Diseases in Vineyards (with Dr. Sharon/Migal ==> ELBIT)

Scientific Publications

Locating the local minima in lens design with machine learning

Kononova, A.V., Shir, O.M., Tukker, T., Frisco, P., Zeng, S., Bäck, T.
Current Developments in Lens Design and Optical Engineering XXII 11814, 1181402
2021

Addressing the Multiplicity of Solutions in Optical Lens Design as a Niching Evolutionary Algorithms Computational Challenge

Kononova, A.V., Shir, O.M., Tukker, T., Frisco, P., Zeng, S., Bäck, T.
Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2021, New York, NY, USA, ACM Press (2021) 1596–1604
2021

Introductory Mathematical Programming for EC

Shir, O.M.
Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2021, New York, NY, USA, ACM Press (2021)
2021

Sequential Experimentation by Evolutionary Algorithms

Shir, O.M., Bäck, T.
Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2021, New York, NY, USA, ACM Press (2021)
2021

Multi-level evolution strategies for high-resolution black-box control

Shir, O.M., Xi, X., Rabitz, H.
Journal of Heuristics (2021), Springer US
2021

Automated Feature Detection of Black-Box Continuous Search-Landscapes using Neural Image Recognition

Yazmir, B., Shir, O.M.
Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2021, New York, NY, USA, ACM Press (2021) 213–214
2021

Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study

Kocaman, V., Shir, O.M., Bäck, T.
Proceedings of the 25th International Conference on Pattern Recognition, ICPR2020 (2021) 10404–10411
2021

Benchmarking Discrete Optimization Heuristics with IOHprofiler.

Doerr, C., Ye, F., Horesh, N., Wang, H., Shir, O.M., Bäck, T.
Applied Soft Computing 88 (2020) 106027
2020

On the Covariance-Hessian Relation in Evolution Strategies.

Shir, O.M., Yehudayoff, A.
Theoretical Computer Science 801 (2020) 157—174
2020

Predict or Screen Your Expensive Assay? DoE vs. Surrogates in Experimental Combinatorial Optimization.

Horesh, N., Bäck, T., Shir, O.M.
In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2019 ,2019, Ed. ,ACM Press New York, NY, USA, Pages 274?284
2019

Statistical Learning in Soil Sampling Design Aided by Pareto Optimization.

Israeli, A., Emmerich, M., Litaor, M., Shir, O.M.
In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2019 ,2019, Ed. ,ACM Press New York, NY, USA, Pages 1198?1205
2019

Bayesian Performance Analysis for Black-Box Optimization Benchmarking.

Calvo, B., Shir, O.M., Ceberio, J., Doerr, C., Wang, H., Bäck, T., Lozano, J.A.
In Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2019 ,2019, Ed. ,ACM Press New York, NY, USA, Pages 1789?1797
2019

Compiling A Benchmarking Test-Suite For Combinatorial Black-Box Optimization: A Position Paper.

Shir, O.M., Doerr, C., Bäck, T.
In Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO-2018 ,2018, ACM Press Ed. , New York, NY, USA,, Pages 1753?1760
2018

Evolution Strategies.

Emmerich, M.T.M., Shir, O.M., Wang, H.
In Handbook of Heuristics. ,2018, Martí R., Panos P., Resende M. Ed. ,Springer Cham , Pages 1-31
2018

On the Statistical Learning Ability of Evolution Strategies

Shir, O.M., Yehudayoff, A.
In Proceedings of the 14th ACM/SIGEVO Conference on Foundations of Genetic Algorithms FOGA-2017 ,2017, ACM Press Ed. ,ACM Press New York, NY, US, Pages 127?138
2017

Protein Design by Multiobjective Optimization: Evolutionary and Non-Evolutionary Approaches.

Belure, S.V., Shir, O.M., Nanda, V.
In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2017 ,2017, Ed. ,ACM Press New York, USA, Pages 1081?1088
2017

Searching for the Pareto frontier in multi-objective protein design.

Nanda, V., Belure, S.V., Shir, O.M.
Biophysical Reviews 2017 Volume 9 Issue 4 Pages 339?344
2017

Solving Structures of Pigment-Protein Complexes as Inverse Optimization Problems using Decomposition.

Lahav, Y., Shir, O.M., Noy, D.
In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2017, ,2017, Ed. ,ACM Press New York, NY, USA,, Pages 1169?1176
2017

Genetic background and environmental conditions drive metabolic variation in wild type and transgenic soybean (Glycine max) seeds

Cohen H, Shir OM, Yu Y, Hou W, Sun S, Han T, Amir R.
Plant Cell and Environment 2016 Volume 39 Pages 1805-17
2016

Multilevel Evolution Strategies for Multigrid Problems.

Shir, O.M.
ACM Press New York, NY, USA, ,2016
2016

On the Capacity of Evolution Strategies to Statistically Learn the Landscape.

Shir, O.M., Roslund, J., Yehudayoff, A.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2016, 2016 Pages 151-152
2016

Efficient Isothermal Titration Calorimetry Technique Identifies Direct Interaction of Small Molecule Inhibitors with the Target Protein.

Gal, M., Bloch I., Shechter, N., Romanenko, O., Shir, O.M.
Comb Chem High Throughput Screen 2016 Volume 19 Issue 1 Pages 4-13
2016

Exploring the complexity of quantum control optimization trajectories.

Nanduri, A., Shir, O.M., Donovan, A., Ho, T.-S., Rabitz, H.
Physical Chemistry Chemical Physics 2015 Volume 17 Issue 1 Pages 334?347
2015

Efficient retrieval of landscape Hessian: Forced optimal covariance adaptive learning

Shir, O.M., Roslund, J., Whitley, D., Rabitz, H.
Physical Review E 2014 Volume 89(6) 063306
2014

Pareto Landscapes Analyses via Graph-Based Modeling for Interactive Decision-Making.

Shir, O.M., Chen, Sh., Amid, D., Margalit, O., Masin, M., Anaby-Tavor, A., Boaz, D.
In EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation V. Advances in Intelligent Systems and Computing ,2014, Tantar AA. et al. Ed. ,Springer, Cham , Pages 97?113
2014