AIConfPaper
← Search

Felix X. Yu

10 accepted papers

2025

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation

Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu +4
ICML 2025poster

Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe

Chong You, Rajesh Jayaram, Ananda Theertha Suresh, Robin Nittka, Felix X. Yu, Sanjiv Kumar
NeurIPS 2025poster

Dual encoder (DE) models, where a pair of matching query and document are embedded into similar vector representations, are widely used in information retrieval due to their simplicity and scalability. However, the Euclidean geometry of the embedding space limits the expressive power of DEs, which m…

Cited by 0Source ↗Scholar ↗
2025

Scalable In-context Ranking with Generative Models

Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit S Dhillon, Felix X. Yu
NeurIPS 2025poster

In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). Whi…

Cited by 0Source ↗Scholar ↗
2025

Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention

Chong You, Kan Wu, Zhipeng Jia, Lin Chen, Srinadh Bhojanapalli, Jiaxian Guo +13
NeurIPS 2025poster

The discovery of the *lazy neuron phenomenon* (Li et al., 2022), where fewer than 10% of the feedforward networks (FFN) parameters in trained Transformers are activated per token, has spurred significant interests in *activation sparsity* for enhancing large model efficiency. While notable progress…

Cited by 0Source ↗Scholar ↗
2020

Pre-training Tasks for Embedding-based Large-scale Retrieval

Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar
ICLR 2020poster

We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two steps. The retrieval phase first reduces the solution space,…

Cited by 355Source ↗Scholar ↗
2017

Distributed Mean Estimation with Limited Communication

Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, H. Brendan McMahan
ICML 2017poster

Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data wi…

Cited by 424Source ↗PDF ↗Scholar ↗
2017

Learning Discriminative and Transformation Covariant Local Feature Detectors

Xu Zhang, Felix X. Yu, Svebor Karaman, Shih-Fu Chang
CVPR 2017poster

Robust covariant local feature detectors are important for detecting local features that are (1) discriminative of the image content and (2) can be repeatably detected at consistent locations when the image undergoes diverse transformations. Such detectors are critical for applications such as image…

Cited by 157PDF ↗code ↗Scholar ↗
2015

An Exploration of Parameter Redundancy in Deep Networks With Circulant Projections

Yu Cheng, Felix X. Yu, Rogerio S. Feris, Sanjiv Kumar, Alok Choudhary, Shi-Fu Chang
ICCV 2015poster

We explore the redundancy of parameters in deep neural networks by replacing the conventional linear projection in fully-connected layers with the circulant projection. The circulant structure substantially reduces memory footprint and enables the use of the Fast Fourier Transform to speed up the co…

Cited by 407PDF ↗Scholar ↗
2015

Fast Orthogonal Projection Based on Kronecker Product

Xu Zhang, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar, Shengjin Wang, Shi-Fu Chang
ICCV 2015poster

We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications. In this, a structured matrix is formed by the Kronecker product of a series of smaller orthogonal matrices. This achieves O(dlogd) computational comp…

Cited by 55PDF ↗Scholar ↗