Farzaneh Mirzazadeh  Farzaneh Mirzazadeh photo         

contact information

Machine Learning Researcher in MIT IBM Watson AI Lab
Cambridge, MA, USA





  • Ph.D. in Computer Science, University of Alberta.
  • M.Sc. in Computer Science, University of Alberta.
  • M.Sc. in Computer Engineering, Focused on Artificial Intelligence, Sharif University of Technology.
  • B.Sc. in Computer Engineering, Amirkabir University of Technology.

Research keywords

  • Multimodal representation learning, Co-embedding, Joint embedding
  • Wasserstein embedding, optimal transport, point clouds, word2cloud
  • Logic embedding, hierarchy embedding, combining learning and reasoning, word2ball
  • Embedding: structured embedding, metric learning
  • Inference-free structured output prediction
  • Association learning, link prediction
  • Matrix and tensor completion, multi-label classification, zero-shot learning
  • Deep structures: Siamese networks, bilinear models, energy based models
  • Convex modeling of machine learning problems
  • Non-convex global optimization
  • Data Dependent Loss Functions 

Publications and Theses

  • Charlie Frogner, Farzaneh Mirzazadeh, Justin Solomon, Learning Embeddings into Entropic Wasserstein Spaces, ICLR 2019. (Paper)
  • Farzaneh Mirzazadeh, Solving Association Problems with Convex Co-embedding, University of Alberta, 2016 (PhD Thesis)
  • Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Nan Ding, and Dale Schuurmans, Embedding Inference for Structured Multilabel Prediction, Neural Information Processing Systems, 2015. (NIPS15Poster
  • Farzaneh Mirzazadeh, Martha White, Andras Gyorgy, and Dale Schuurmans, Scalable metric learning for co-embedding, European Conference on Machine Learning , 2015, Oral (PaperTalk SlidesPoster
  • Farzaneh Mirzazadeh, Yuhong Guo and Dale Schuurmans Convex co-embedding. In Twenty-Eighth Annual Conference on Artificial Intelligence, 2014, Oral (PaperTalk SlidesPoster)
  • Farzaneh Mirzazadeh and Dale Schuurmans,  Data dependent loss functions for focused generalization and transfer learning, In ICML workshop, 2011 (ICMLWS11)
  • Farzaneh Mirzazadeh, Using SNP data to predict radiation toxicity for prostate cancer patients, MSc thesis, University of Alberta, 2009.
  • Farzaneh Mirzazadeh, and Saeed Bagheri Shouraki, Online recognition of handwritten Persian words using a novel hierarchical fuzzy system, (ICSCIS 07)
  • Farzaneh Mirzazadeh, Online recognition of handwritten Persian words, MSc thesis, Sharif University of Technology, 2007
  • Farzaneh Mirzazadeh, Babak Behsaz, and Hamid Beigy, A new learning algorithm for MAXQ hierarchical reinforcement learning method, in International Conference on Information and Communication Technology - (IEEE ICICT '07)
  • Reza Safabakhsh and Farzaneh Mirzazadeh, AUT-Talk: a Farsi talking head, in Information and Communication Technologies, (IEEE ICTTA 06)
  • Farzaneh Mirzazadeh, Design and implementation of a Farsi talking head (including a Farsi text to speech synthesis engine), BSc thesis, Amirkabir University of Technology, 2005.