The paper's abstract is as follows: “In machine learning, tasks like making predictions using a model and learning model parameters can often be formulated as optimization problems. The feasibility of using a machine learning model depends on the efficiency with which the corresponding optimization problems can be solved. As such, the area of machine learning throws up many challenges and interesting problems for research in the field of optimization. While in some cases, it is possible to directly apply off-the-shelf optimization methods for problems in machine learning, in many other cases, it becomes necessary to develop optimization algorithms that are tailor-made for specific problems. On the other hand, developing optimization algorithms for specific problem domains can itself be helped by machine learning techniques. Learning optimization algorithms from data can help relieve the tedious effort required to develop optimization methods for new problem domains. The challenge here is to appropriately parameterize the space of algorithms for different optimization problems. In this context, we explore the interplay between the areas of optimization and machine learning and contribute to specific problems of interest that lie in the overlap of these fields.”
Native of Odisha, Pritish completed B.E. in Electrical and Electronics Engineering from Birla Institute of Technology and Science (BITS), Pilani, India. He also worked as a Junior Research Fellow at the Central Electronics Engineering Research Institute (CEERI), Pilani, India. He pursued PhD in Computer Science and Engineering at the Center of Visual Information Technology(CVIT) at IIIT-Hwhere he focused on Machine Learning, Optimization and Computer Vision. In addition to his Doctoral dissertation, many of his research publications from CVIT include:


  • Learning to Round for Discrete Labeling Problems, International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
  • Partial Linearization-based Optimization for Multi-class SVM. European Conference on Computer Vision (ECCV), 2016
  • Optimizing Average Precision using Weakly Supervised Data, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.
  • Efficient Optimization for Average Precision SVM, In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2014.
Pritesh Mohapatra also won the honourable mention award for his paper, The Efficient Optimization for Rank-based Loss Functions, at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.