Farzaneh Mirzazadeh — accepted AI-conference papers

2025

Enhancing Decision Making Through the Integration of Large Language Models and Operations Research Optimization

Segev Wasserkrug, Leonard Boussioux, Dick den Hertog, Farzaneh Mirzazadeh, Ş. İlker Birbil, Jannis Kurtz +1

AAAI 2025technical

Many critical business and societal decisions in areas such as supply chain and healthcare involve numerous potential actions, complex constraints, and goals that can be modeled as objective functions. Mathematical optimization, a core area in Operations Research (OR), provides robust, mathematicall…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

GC-Flow: A Graph-Based Flow Network for Effective Clustering

Tianchun Wang, Farzaneh Mirzazadeh, Xiang Zhang, Jie Chen

ICML 2023poster

Graph convolutional networks (GCNs) are *discriminative models* that directly model the class posterior $p(y|\mathbf{x})$ for semi-supervised classification of graph data. While being effective, as a representation learning approach, the node representations extracted from a GCN often miss useful in…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2019

Alleviating Label Switching with Optimal Transport

Pierre Monteiller, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin M Solomon, Mikhail Yurochkin

NeurIPS 2019poster

Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior statistics using standard Monte Carlo procedures. This issue arises due to invariance of the posterior under actions of a group; for example, permuting the ordering of…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2019

Hierarchical Optimal Transport for Document Representation

Mikhail Yurochkin, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin M Solomon

NeurIPS 2019poster

The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances between documents suffer from either an inability to incorporate semantic similarities between words or from scalability issues. As an alternative, we introduce hierarc…

Cited by 107 Source ↗PDF ↗code ↗Scholar ↗

2019

Learning Embeddings into Entropic Wasserstein Spaces

Charlie Frogner, Farzaneh Mirzazadeh, Justin Solomon

ICLR 2019poster

Despite their prevalence, Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete probability distributions in a Wasserstein…

Cited by 44 Source ↗PDF ↗Scholar ↗

2015

Embedding Inference for Structured Multilabel Prediction

Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Nan Ding, Dale Schuurmans

NeurIPS 2015poster

A key bottleneck in structured output prediction is the need for inference during training and testing, usually requiring some form of dynamic programming. Rather than using approximate inference or tailoring a specialized inference method for a particular structure---standard responses to the scal…

Cited by 23 Source ↗PDF ↗Scholar ↗