Learning and Inference via Maximum Inner Product Search

By Stephen O. Mussmann, Stefano Ermon. 2016

61 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

1. Sanjiv Kumar
2. Ruiqi Guo
3. David Simcha
4. Mohit Bansal
5. Hao Hao Tan

In Optimization & Training

1. Mohit Bansal
2. Sanjiv Kumar
3. Quan Geng
4. David Simcha
5. Philip Sun
6. Erik M. Lindgren
7. Ruiqi Guo
8. Hao Hao Tan

Citations in the corpus

• Vokenization: Improving Language Understanding via Contextualized, Visually-Grounded Supervision (2020, methodology): “1 could be formulated as Maximum Inner Product Search (Mussmann and Ermon, 2016)).”
• Accelerating Large-Scale Inference with Anisotropic Vector Quantization (2019, methodology): “Lately, MIPS has also been applied to training tasks such as scalable gradient computation in large output spaces (Yen et al., 2018), efficient sampling for speeding up softmax computation (Mussmann & Ermon, 2016) and sparse updates in end-to-end trainable memory systems (Pritzel et al., 2017).”