Farzaneh Mirzazadeh  Farzaneh Mirzazadeh photo         

contact information

Machine Learning Research Staff Member in MIT IBM Watson AI Lab
Cambridge, MA, USA
  

links


profile


 

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
  • Generative modeling
  • Copula, Quantile functions, Ranking, etc. 

Selected Publications and Theses

  • Mikhail Yurochkin, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin Solomon, Hierarchical Optimal Transport for Document Representation, NeurIPS 2019. (NeurIPS19_Paper)
    Topics:  Document embedding, Hierarchical optimal transport, structured representation.
  • Charlie Frogner, Farzaneh Mirzazadeh, Justin Solomon, Learning Embeddings into Entropic Wasserstein Spaces, ICLR 2019. (ICLR19_Paper) (ICLR19_Poster)
    Topics: Object2cloud embedding, increased embedding capacity, Wasserstein space.
  • Farzaneh Mirzazadeh, Solving Association Problems with Convex Co-embedding, University of Alberta, 2016 (PhD Thesis)
    Topics: Multi-modal embedding, assocaition learning, graph embedding

  • Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Nan Ding, and Dale Schuurmans, Embedding Inference for Structured Multilabel Prediction, Neural Information Processing Systems, 2015. (NIPS15-Paper, NIPS15_Poster)

    Topics: Combination of symbolic reasoning and learning, object2ball embedding, logic embedding, multilabel classification, sructured prediction

  • Farzaneh Mirzazadeh, Martha White, Andras Gyorgy, and Dale Schuurmans, Scalable metric learning for co-embedding, European Conference on Machine Learning , 2015, Oral (ECML15-PaperECML15-Talk SlidesECML15-Poster
    Topics: Equivalence of global and locally optimal solutions.

  • 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.

Education

  • Ph.D. in Machine Learning, Department of Computer Science, University of Alberta.