REVIEW 7 cited by
Online learning of quantum processes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Among recent insights into learning quantum states, online learning and shadow tomography procedures are notable for their ability to accurately predict expectation values even of adaptively chosen observables. In contrast to the state case, quantum process learning tasks with a similarly adaptive nature have received little attention. In this work, we investigate online learning tasks for quantum processes. Whereas online learning is infeasible for general quantum channels, we show that channels of bounded gate complexity as well as Pauli channels can be online learned in the regret and mistake-bounded models of online learning. In fact, we can online learn probabilistic mixtures of any exponentially large set of known channels. We also provide a provably sample-efficient shadow tomography procedure for Pauli channels. Our results extend beyond quantum channels to non-Markovian multi-time processes, with favorable regret and mistake bounds, as well as a shadow tomography procedure. We complement our online learning upper bounds with mistake as well as computational lower bounds. On the technical side, we make use of the multiplicative weights update algorithm, classical adaptive data analysis, and Bell sampling, as well as tools from the theory of quantum combs for multi-time quantum processes. Our work initiates a study of online learning for classes of quantum channels and, more generally, non-Markovian quantum processes. Given the importance of online learning for state shadow tomography, this may serve as a step towards quantum channel variants of adaptive shadow tomography.
Forward citations
Cited by 7 Pith papers
-
Instance-Optimal Matrix Multiplicative Weight Update and Its Quantum Applications
A new potential-based algorithm achieves instance-optimal O(sqrt(T·S(X||I/d))) regret for matrix LEA with the same complexity as MMWU, using a one-sided Jensen trace inequality.
-
Quantum channel tomography: optimal bounds and a Heisenberg-to-classical phase transition
Optimal quantum channel tomography query complexity has a Heisenberg-to-classical phase transition at dilation rate τ=1: Θ(rd₁d₂/ε) on the boundary and Θ(rd₁d₂/ε²) away from it.
-
Coherent Swap Regret and Channel-Proof Learning
Introduces coherent swap regret against local CPTP maps and proves a three-level landscape where non-unital measurement-preparation channels force Theta(sqrt(d T log d)) minimax regret while unital channels have zero regret.
-
Quantum channel tomography: optimal bounds and a Heisenberg-to-classical phase transition
Quantum channel tomography query complexity transitions from Heisenberg scaling Θ(r d1 d2 / ε) at dilation rate τ=1 to classical scaling Θ(r d1 d2 / ε²) for τ ≥ 1+Ω(1).
-
Maximum channel entropy principle and microcanonical channels
A maximum-entropy principle for quantum channels yields thermal channels with exponential form, analogous to thermal states.
-
Thermalization with partial information
A maximum channel entropy principle, backed by a microcanonical-style derivation, identifies the canonical noisy channel that models thermalization under partial information.
-
Efficient Noisy Quantum State and Process Tomography
The paper proposes tomography by estimating only low-weight Pauli coefficients of noisy random-circuit states and processes, with claimed complexity independent of depth and noise strength — but the supporting path-co...
Discussion (0). Sign in to comment.