GAIA introduces a geometry-adaptive integral autoencoder that unifies forward, boundary-value, and inverse PDE operator learning on arbitrary domains via geometry tokens and cross-attention.
mega hub Mixed citations
Adam: A Method for Stochastic Optimization
Mixed citation behavior. Most common role is method (50%).
2073
Pith papers citing it
Method
50% of classified citations
abstract
We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
hub tools
citation-role summary
method 117
background 97
other 9
baseline 8
dataset 2
citation-polarity summary
claims ledger
- abstract We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little
authors
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
ShardNet enforces non-convex polyhedral safety constraints in neural controllers by construction via a differentiable projection layer, achieving 100% verified safety and over 3x larger safe sets than prior methods on double integrator benchmarks.
The paper establishes the first finite-time convergence rate of 1/T^{2/13} for classical Adam (with bias correction, no extra steps) in nonsmooth nonconvex optimization under heavy-tailed noise with β1=β2.
Machine learning discovers a tube-seeding strategy for IBP reduction of Feynman integrals that scales linearly with numerator power, demonstrated on rank-20 2-loop 5-point integrals.
TAKO demonstrates real-time adversarial takeover of robotic diffusion policies via reusable universal patches on visual inputs, achieving 100% success in steering attacker-chosen trajectories across multiple tasks, encoders, and diffusion methods.
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.
Introduces REST-ASMR multimodal dataset of PPG, stimuli, and continuous annotations for ASMR research, validated with 97% responder rate, significant agreement, PPG deceleration, and BiLSTM achieving 75.51% frame-level accuracy under strict subject-video independent 4-fold CV.
PINNs are used to non-parametrically infer the neutron star EOS from NICER and pulsar data, producing M_max = 2.06 M_sun, R_1.4 = 12.85 km, and a reproducible speed-of-sound softening at 2-4 rho_0 consistent with quark-hadron crossover.
OpenVMR uses normalizing flow to detect out-of-distribution queries and performs moment retrieval only on in-distribution queries.
Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
Ensembits is the first tokenizer of protein conformational ensembles that outperforms static tokenizers on RMSF prediction and matches them on function and mutation tasks while using less pretraining data.
In the high-dimensional limit the spherical Boltzmann machine admits exact equations for training dynamics, Bayesian evidence, and cascades of phase transitions tied to mode alignment with data, which connect to generative phenomena including double descent and out-of-equilibrium biases.
Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
SLayerGen generates crystals invariant to any space or layer group via autoregressive lattice and Wyckoff sampling plus equivariant diffusion, achieving gains over bulk models on diperiodic materials after correcting a prior loss inconsistency for hexagonal groups.
3DSS is the first differentiable surface splatting renderer that recovers shape, spatially-varying BRDF materials, and HDR illumination from multi-view images via a coverage-based compositing model derived from reconstruction kernels.
PF-AGD is the first parameter-free deterministic accelerated first-order method with Õ(ε^{-5/3} log(1/ε)) complexity for smooth non-convex optimization.
STARE uses step-wise RL to attack multimodal models, achieving 68% higher attack success rate while revealing that adversarial optimization concentrates conceptual toxicity early and detail toxicity late in the generation trajectory.
Qvine uses vine copula-inspired quantum circuit structures to achieve linear or quadratic depth scaling for loading high-dimensional distributions with high approximation quality.
Neural networks optimized solely on crossing symmetry reconstruct CFT correlators from minimal input data to few-percent accuracy across generalized free fields, minimal models, Ising, N=4 SYM, and AdS diagrams.
MMGait provides a new multi-sensor gait dataset and OmniGait baseline to support single-modal, cross-modal, and unified multi-modal person identification from walking patterns.
Neural simulation-based inference on unbinned top-quark pair data at 13 TeV yields improved gluon PDF precision over traditional binned analyses while incorporating experimental and theoretical uncertainties.
Adam-HNAG is a splitting-based reformulation of Adam that yields the first convergence proof for Adam-type methods, including accelerated rates, in convex smooth optimization.
The paper introduces the CMCC-ReID task, constructs the SYSU-CMCC benchmark dataset, and proposes the PIA network with disentangling and prototype modules that outperforms prior methods on combined modality and clothing variations.
Quantitative Bayesian inference using a deep-learning emulator detects 0.018-0.020 M_sun of helium in the Type Ic supernova 2014L.
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.
-
Qvine: Vine Structured Quantum Circuits for Loading High Dimensional Distributions
Qvine uses vine copula-inspired quantum circuit structures to achieve linear or quadratic depth scaling for loading high-dimensional distributions with high approximation quality.
-
Automated discovery of heralded ballistic graph state generators for fusion-based photonic quantum computation
A two-pass optimization framework with polynomial-based simulation discovers heralded ballistic circuits for 3-5 qubit graph states achieving up to 7.5x higher success probabilities than fusion baselines, including first known circuits for some 5-qubit states.
-
Diffusion-warm sampling of the XY model enables fast thermalization at scale
A temperature-conditioned diffusion model trained on small XY lattices produces accurate larger-lattice samples and cuts MCMC thermalization time by roughly 10x.
-
Uncovering Latent Structures in Robust Pulse Sequences: A Model-Based Reinforcement Learning Approach for Adaptable Quantum Control
Model-based RL trains a neural network embedding the Hamiltonian to output robust pulses for arbitrary rotations under varying parameters in a single-spin system, achieving GRAPE-comparable fidelity while revealing consistent phase structures.
-
Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning
CRiSP uses neural-guided MCTS and curriculum learning to insert Clifford prefixes before parameterized rotations in VQAs, yielding mean 3.17x and max 45x gains in energy accuracy on 22-qubit QAOA benchmarks versus prior Clifford initializers.
-
Generating Non-Decomposable Maps with Differentiable Semidefinite Programming
A differentiable SDP method generates positive non-decomposable maps, identifies parametrized families, and explores open problems like the PPT square conjecture.
-
Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
NVQLS introduces the first hybrid quantum-classical unsupervised operator learning method for parametric PDEs via Legendre-Galerkin weak form, sign ambiguity resolution, and neural embedding.
-
Architecture Shape Governs QNN Trainability: Jacobian Null Space Growth and Parameter Efficiency
At fixed encoding budget, serial QNN architectures suffer unbounded structural gradient starvation via rank(J) ≤ 2L+1 while parallel ones keep full Jacobian rank and better parameter efficiency when adding feature-map layers.
-
Magic-Informed Quantum Architecture Search
A Monte Carlo Tree Search with GNN-based magic estimation biases quantum circuit search toward target nonstabilizerness levels and yields better results on ground-state energy and state approximation problems.
-
Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks
QIBP adapts interval bound propagation to quantum neural networks for certified adversarial robustness via interval and affine arithmetic implementations.
-
Learning Lindblad Dynamics of a Superconducting Quantum Processor
LIMINAL fits nested Lindblad models to tomographic data and uses likelihood-ratio tests to identify minimal dynamics for a five-qubit superconducting processor, supporting three-local Hamiltonian terms and two-local dissipation but not three-local dissipation.
-
The most discriminable quantum states in the multicopy regime
k-designs achieve maximal multi-copy discriminability for pure states when N suffices, mixed states outperform beyond that, and quantum offers quadratic advantage over classical in Bayes capacity terms.
-
Graph-Conditioned Meta-Optimizer for QAOA Parameter Generation on Multiple Problem Classes
A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
-
Variance Geometry of Exact Pauli-Detecting Codes: Continuous Landscapes Beyond Stabilizers
Exact Pauli-detecting codes form continuous connected families in a variance geometry parameterized by λ* from Knill-Laflamme conditions, with stabilizer codes occupying only discrete measure-zero subsets.
-
Composite quantum gates simultaneously compensated for multiple errors
New symmetric five-pulse and longer composite sequences are constructed that compensate amplitude, detuning, and duration errors for X and Hadamard gates via derivative cancellation in the Cayley-Klein parametrization and numerical infidelity minimization.
-
Lund Plane to Bloch (LP2B) Encoding for Object and Polarization Tagging with Quantum Jet Substructure
LP2B encoding converts Lund plane jet representations into Bloch sphere qubit states, enabling a QTTN that matches classical LundNet performance on polarization tagging and W/top tagging with three orders of magnitude fewer parameters and improved low-data regime results.
-
Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States
Dilated RNN wave functions induce power-law correlations for the critical 1D transverse-field Ising model and the Cluster state, unlike the exponential decay of conventional RNN ansatze.
-
A hardware efficient quantum residual neural network without post-selection
A quantum residual neural network using deterministic mixtures of identity and variational unitaries to enable post-selection-free residual learning with 10x fewer gates and reported accuracies of 99% binary and 80% multi-class on image datasets.
-
Quantum Masked Autoencoders for Vision Learning
Quantum masked autoencoders reconstruct masked MNIST-family images in quantum states and achieve 12.86% higher average classification accuracy than prior quantum autoencoders under masking.
-
Meson spectroscopy of exotic symmetries of Ising criticality in Rydberg atom arrays
Rydberg arrays realize Ising criticality with E8 mass spectra in chains and first signatures of D8^(1)-organized bound states from interchain confinement in ladders.
-
The Lie Algebra of XY-mixer Topologies and Warm Starting QAOA for Constrained Optimization
The paper decomposes dynamical Lie algebras of XY-mixer topologies and demonstrates warm-starting QAOA via pre-training on restricted generators to improve convergence on constrained optimization problems.
-
Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor
Experimental runs on a superconducting quantum processor demonstrate that 20-qubit quantum neural networks are more resistant to adversarial attacks than classical networks, with adversarial training further improving robustness and empirical bounds closely matching theory.
-
Measurement-based quantum machine learning
The authors introduce MuTA as a universal quantum neural network for MBQC and numerically demonstrate its ability to learn gates, classify quantum states, and process data under noise, including photonic hardware constraints.
-
An Operational Framework for Nonclassicality in Quantum Communication Networks
A variational optimization framework computes linear classical bounds on network input/output probabilities whose violation certifies nonclassicality, finding entanglement necessary for nonclassicality in single-sender broadcast networks but not in multi-sender networks.
-
Structured Factorization Approaches for Quantum State Tomography
A unified structured factorization framework for quantum state tomography that parametrizes the density matrix as FF^dagger, supports multiple priors, provides sample complexity bounds, and introduces projected gradient descent and power-method algorithms.
-
Tensor network characterization and mitigation of readout errors
An MPO-based tensor network model for readout errors captures spatial correlations with near-linear sample cost, outperforming uncorrelated approximations in quantum information tasks.
-
When does dissipation help neural surrogates learn open quantum dynamics?
Dissipation enhances neural surrogate learnability of open quantum dynamics in spin chains at intermediate sizes via contraction, but fidelity metrics must separate genuine dynamics from steady-state trivialization.
-
Quantum Kernels are Spectral Tensor Networks
Quantum kernels are spectral tensor networks because their Fourier coefficient tensors are matrix product operator factorizations, with kernel target alignment acting as Frobenius cosine similarity on frequency grids.
-
All-valid-state HOBO encoding for constrained combinatorial optimization on NISQ devices
Authors introduce AVS-HOBO encoding for TSP that eliminates one penalty term via cyclic mapping and report improved VQE performance in noiseless simulations and hardware runs compared to standard HOBO.
-
Separation of Statistical Complexity and Trainability in Variational Quantum Circuits
Statistical complexity measures reach random-like behavior in finite-depth variational circuits before trainability degrades due to locality effects in studied models.
-
QnRL: Quantum-Native Reinforcement Learning
QnRL is a distributional quantum RL framework that distills conditional action policies from moments of quantum generative models in Hilbert space via the QuAK algorithm, reporting higher scores and fewer parameters than baselines.
-
Vector Magnetometry with Broadband Microwave Fields in Nitrogen-Vacancy Centers in Diamond
Simulation study of broadband microwave transmission through NV centers with orthogonal polarizations and DNN readout enables vector magnetometry at 5-100 pT/√Hz sensitivity down to 25 μT fields.
-
Bargmann Zeros as a Diagnostic of the Tunneling Transition in Double-Well Quantum Systems
Bargmann zeros of double-well eigenstates condense on the imaginary axis as a signature of the tunneling regime, obtained via variational wavefunctions projected to the Fock basis.
-
Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
Q-PhotoNAS applies genetic algorithm search to jointly optimize classical preprocessing, phase encoding, and photonic circuit structure for hybrid quantum-classical models, reporting 99.44% and 98.78% accuracy on Digits and MNIST with projected photonic QPU inference times.
-
Combining non-parametric quantum states and MERA tensor networks for ground-state optimization
A hybrid method uses fixed quantum annealing states as boundary resources for classical MERA tensor networks to improve ground-state approximations without deeper quantum circuits.
-
CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem
Reinforcement learning policy for qubit mapping reduces SWAP overhead by 65-85% versus standard quantum compilers on MQTBench and Queko benchmark circuits.
-
Quantum End-to-End Learning for Contextual Combinatorial Optimization
QEL is the first quantum end-to-end learning framework for contextual combinatorial optimization using QAOA with a context re-uploading phase-separator, achieving competitive performance with fewer parameters.
-
Training continuously-coupled reconfigurable photonic chips with quantum machine learning
A black-box machine learning technique trains continuously-coupled photonic waveguide arrays to implement target unitaries using limited single- and two-photon measurements without requiring detailed internal models.
-
Universal Neural Propagator: Learning Time Evolution in Many-Body Quantum Systems
The Universal Neural Propagator is a single neural model trained self-supervised to predict time evolution in driven quantum many-body systems across arbitrary protocols and initial states.
-
Quantum Magic in early FTQC: From Diagonal Clifford Hierarchy No-Go Theorems to Architecture Design Blueprints
No-go theorems prove hierarchy level and state-independent sequences cannot maximize operational magic in early FTQC, requiring state-aware differentiable optimization and nonlinear phases for scalable magic generation.
-
GHZ is All You Need: Quantum Sensing with VISTA
VISTA achieves near-Heisenberg scaling in moderately noisy quantum magnetometry by passively evolving a probe, comparing it via swap test to a physics-informed quantum twin circuit, and optimizing only physical parameters with quasi-normalization.
-
Rethinking How to Act: Action-Space Engineering for Reinforcement Learning-Based Circuit Routing in Distributed Quantum Systems
An RL agent with engineered action spaces for distributed quantum circuit routing achieves up to 35% reduction in modeled execution time compared to previous methods.
-
Towards Real-time Control of a CartPole System on a Quantum Computer
A single-qubit quantum reinforcement learning agent solves CartPole faster than classical networks and quantifies shot-count versus control-frequency requirements for real-time closed-loop control on NISQ hardware, including direct electronics programming to reduce latency.
-
Universality of Quantum Gates in Particle and Symmetry Constrained Subspaces
Hardware-efficient gates are universal for state preparation in particle-number and symmetry-constrained subspaces because commutators generate Pauli Z projectors that span the full so(w) and su(w) algebras.
-
Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
A quantum autoencoder purifies adversarial perturbations for quantum classifiers and supplies a confidence score for unrecoverable inputs, claiming up to 68% accuracy gains over prior defenses without adversarial training.
-
One Coordinate at a Time: Convergence Guarantees for Rotosolve in Variational Quantum Algorithms
Rotosolve converges to ε-stationary points for smooth non-convex objectives and ε-suboptimal points under PL, with explicit worst-case rates in the finite-shot regime, outperforming or matching RCD in nuanced ways.
-
Efficient optimisation of multi-parameter quantum control protocols for strongly-coupled systems
Gradient-based optimization of SUPER and FTPE pulse protocols via auto-differentiation and uniTEMPO yields higher preparation fidelities than resonant pi-pulses or standard two-photon excitation, with the advantage increasing at higher temperatures.
-
Efficient $n$-qubit entangling operations via a superconducting quantum router
A superconducting quantum router enables programmable multi-qubit entangling operations, demonstrated with faster preparation of entangled states and RL-trained 2- and 3-qubit gates like Toffoli and Fredkin.
-
Reachability Constraints in Variational Quantum Circuits: Optimization within Polynomial Group Module
A necessary condition for variational quantum circuits to reach exact ground states requires matching module projection norms between input and solution, enabling classical O(n^5) exact solvers for problems like MaxCut.