Forward gradient framework for PQCs unifies SPSA and parameter-shift as limits, introduces QUIVER adaptive optimizer with closed-form measurement allocation, and demonstrates efficient training of 60-qubit circuits on ECG5000 and MNIST.
arXiv preprint arXiv:2202.08587 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
years
2026 9representative citing papers
Dimensional types that persist through MLIR lowering jointly drive numeric representation selection and deterministic memory allocation as coeffects on a single program semantic graph.
Develops randomized-subspace Nesterov accelerated gradient methods with accelerated oracle-complexity guarantees for smooth convex optimization under matrix smoothness and sketch moment assumptions.
Composing dimensional types, program hypergraphs, and b-posits yields depth-independent training memory, grade-preserving geometric updates, Bayesian distillation, and certified warm model rotation for domain AI.
Program Hypergraphs lift binary semantic graphs to arbitrary-arity hyperedges so grade inference, k-simplex joins, and spatial co-location become first-class, jointly analyzable compilation facts.
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
Echo Networks are recurrent networks defined by a single connection matrix with no layers, enabling matrix-based mutation and recombination in neuroevolution, and demonstrated on ECG signal classification.
Design-time Hindley-Milner unification over finitely generated abelian groups is claimed to verify AI model reliability properties and to compute a MAP hypothesis under a restricted Solomonoff prior.
citing papers explorer
-
Adaptive directional gradients for parameterised quantum circuits
Forward gradient framework for PQCs unifies SPSA and parameter-shift as limits, introduces QUIVER adaptive optimizer with closed-form measurement allocation, and demonstrates efficient training of 60-qubit circuits on ECG5000 and MNIST.
-
Dimensional Type Systems and Deterministic Memory Management: Design-Time Semantic Preservation in Native Compilation
Dimensional types that persist through MLIR lowering jointly drive numeric representation selection and deterministic memory allocation as coeffects on a single program semantic graph.
-
Randomized Subspace Nesterov Accelerated Gradient
Develops randomized-subspace Nesterov accelerated gradient methods with accelerated oracle-complexity guarantees for smooth convex optimization under matrix smoothness and sketch moment assumptions.
-
Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI
Composing dimensional types, program hypergraphs, and b-posits yields depth-independent training memory, grade-preserving geometric updates, Bayesian distillation, and certified warm model rotation for domain AI.
-
The Program Hypergraph: Multi-Way Relational Structure for Geometric Algebra, Spatial Compute, and Physics-Aware Compilation
Program Hypergraphs lift binary semantic graphs to arbitrary-arity hyperedges so grade inference, k-simplex joins, and spatial co-location become first-class, jointly analyzable compilation facts.
-
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
-
Introducing Echo Networks for Computational Neuroevolution
Echo Networks are recurrent networks defined by a single connection matrix with no layers, enabling matrix-based mutation and recombination in neuroevolution, and demonstrated on ECG signal classification.
-
Decidable By Construction: Design-Time Verification for Trustworthy AI
Design-time Hindley-Milner unification over finitely generated abelian groups is claimed to verify AI model reliability properties and to compute a MAP hypothesis under a restricted Solomonoff prior.
- Training Non-Differentiable Networks via Optimal Transport