Binary classification with classical instances and quantum labels

@article{Caro2021BinaryCW,
  title={Binary classification with classical instances and quantum labels},
  author={Matthias C. Caro},
  journal={Quantum Machine Intelligence},
  year={2021},
  volume={3},
  pages={1-24}
}
  • Matthias C. Caro
  • Published 2021
  • Computer Science, Physics
  • Quantum Machine Intelligence
In classical statistical learning theory, one of the most well-studied problems is that of binary classification. The information-theoretic sample complexity of this task is tightly characterized by the Vapnik-Chervonenkis (VC) dimension. A quantum analog of this task, with training data given as a quantum state has also been intensely studied and is now known to have the same sample complexity as its classical counterpart. We propose a novel quantum version of the classical binary… Expand

References

SHOWING 1-10 OF 68 REFERENCES
The learnability of unknown quantum measurements
TLDR
This work investigates the information-theoretic upper bounds of sample complexity - how many training samples are sufficient to predict the future behaviour of an unknown target function and shows that learning quantum measurements/states can be mathematically formulated as a neural network. Expand
Quantum Algorithms for Learning and Testing Juntas
TLDR
This article develops quantum algorithms for learning and testing juntas, i.e. Boolean functions which depend only on an unknown set of k out of n input variables, and establishes the following lower bound: any FS-based k-junta testing algorithm requires $$Omega(\sqrt{k})$$ queries. Expand
Quantum learning robust against noise
Noise is often regarded as anathema to quantum computation, but in some settings it can be an unlikely ally. We consider the problem of learning the class of $n$-bit parity functions by makingExpand
Quantum learning Boolean linear functions w.r.t. product distributions
TLDR
The biased quantum Fourier transform introduced in Kanade et al. (2018) is employed to develop efficient quantum algorithms for learning Boolean linear functions on n bits from quantum examples w.r.t. and proves lower bounds on the classical and quantum sample complexities of the learning problem. Expand
Equivalences and Separations Between Quantum and Classical Learnability
TLDR
These results contrast known results that show that testing black-box functions for various properties, as opposed to learning, can require exponentially more classical queries than quantum queries. Expand
Demonstration of quantum advantage in machine learning
TLDR
D. Ristè and colleagues at Raytheon BBN Technologies, with collaborators at IBM, have demonstrated that a quantum advantage already appears with only a few quantum bits and a highly noisy system. Expand
Quantum machine learning: a classical perspective
TLDR
The literature in quantum ML is reviewed and perspectives for a mixed readership of classical ML and quantum computation experts are discussed, with particular emphasis on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Expand
Learning DNF over the uniform distribution using a quantum example oracle
TLDR
It is shown that DNF is efficiently learnable with respect to the uniform distribution by a quantum algorithm using a quantum example oracle, and the notion of classification noise to the quantum setting is generalized and shows that the quantum DNF algorithm learns even in the presence of such noise. Expand
Quantum hardness of learning shallow classical circuits
TLDR
The main technique in this result is to establish a connection between the quantum security of public-key cryptosystems and the learnability of a concept class that consists of decryption functions of the cryptos system. Expand
The learnability of quantum states
  • S. Aaronson
  • Computer Science, Physics
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
  • 2007
TLDR
This theorem has the conceptual implication that quantum states, despite being exponentially long vectors, are nevertheless ‘reasonable’ in a learning theory sense and has two applications to quantum computing: first, a new simulation of quantum one-way communication protocols and second, the use of trusted classical advice to verify untrusted quantum advice. Expand
...
1
2
3
4
5
...