Information-theoretic generalization bounds for learning from quantum data

no code implementations • 9 Nov 2023 • Matthias Caro, Tom Gur, Cambyse Rouzé, Daniel Stilck França, Sathyawageeswar Subramanian

Learning tasks play an increasingly prominent role in quantum information and computation.

Generalization Bounds Learning Theory +1

Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation

no code implementations • 27 Jan 2023 • Hayata Yamasaki, Sathyawageeswar Subramanian, Satoshi Hayakawa, Sho Sonoda

To address this problem, we develop a quantum ridgelet transform (QRT), which implements the ridgelet transform of a quantum state within a linear runtime $O(D)$ of quantum computation.

Quantum Machine Learning

Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions

no code implementations • NeurIPS 2020 • Hayata Yamasaki, Sathyawageeswar Subramanian, Sho Sonoda, Masato Koashi

Here, we develop a quantum algorithm for sampling from this optimized distribution over features, in runtime $O(D)$ that is linear in the dimension $D$ of the input data.

BIG-bench Machine Learning Quantum Machine Learning

A Quantum Search Decoder for Natural Language Processing

no code implementations • 9 Sep 2019 • Johannes Bausch, Sathyawageeswar Subramanian, Stephen Piddock

Probabilistic language models, e. g. those based on an LSTM, often face the problem of finding a high probability prediction from a sequence of random variables over a set of tokens.