O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar. O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]

This author has not been identified. Look up 'Chulhee Yun' in GoogleThis author has not been identified. Look up 'Yin-Wen Chang' in GoogleThis author has not been identified. Look up 'Srinadh Bhojanapalli' in GoogleThis author has not been identified. Look up 'Ankit Singh Rawat' in GoogleThis author has not been identified. Look up 'Sashank J. Reddi' in GoogleThis author has not been identified. Look up 'Sanjiv Kumar' in Google

runs on WebDSL