arXiv subjects

Junghyun Lee

Publications and source records attributed to Junghyun Lee.

At least 37 records · Page 2Linked to original sources

arXiv2025

Probability-Flow ODE in Infinite-Dimensional Function Spaces

Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.

cs.LG↗

arXiv2025

Quantum decoherence of nitrogen-vacancy spin ensembles in a nitrogen spin bath in diamond under dynamical decoupling

The negatively charged nitrogen-vacancy (NV) center in diamond has emerged as a leading qubit platform for quantum technology applications. One of the key challenges for NV-based quantum applications is building an accurate model to predict its decoherence properties and their quantum nature. In this study, we combine theory and experiment to investigate NV decoherence dynamics in the presence of nitrogen donor (P1 center) baths, which is one of the dominant decoherence sources in diamond. We employ a cluster-correlation expansion (CCE) method to compute the NV decoherence under the Hahn-echo (HE) and Carr-Purcell-Meiboom-Gill (CPMG) pulse sequences at various P1 concentrations from 1ppm to 300 ppm. We show that the coherence time (T2) increases with the number of pi pulses applied, indicating that the NV spin is decoupled from the P1 bath. Notably, we find that T2 scales quadratically as a function of the pulse number, on a logarithmic scale, as opposed to the linear scaling predicted by widely accepted semi-classical theories in the literature. In our experiment, we measure the CPMG signal for two diamond samples with high P1 concentrations of 0.8ppm and 13ppm. We demonstrate that the T2 scaling is indeed quadratic, thus confirming our theoretical predictions. Our results show that the quantum bath model combined with the CCE method can accurately capture the quantum nature of the P1-driven NV decoherence. Our study opens a new avenue for developing a complete noise model that could be used to optimize the performance of NV-based quantum devices.

quant-ph↗

arXiv2025

A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits

We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is guaranteed to be convex and numerically tight. We show that this is on par or improves upon known CSs for various GLMs, including Gaussian, Bernoulli, and Poisson. In particular, for the first time, our CS for Bernoulli has a $\mathrm{poly}(S)$-free radius where $S$ is the norm of the unknown parameter. Our first technical novelty is its derivation, which utilizes a time-uniform PAC-Bayesian bound with a uniform prior/posterior, despite the latter being a rather unpopular choice for deriving CSs. As a direct application of our new CS, we propose a simple and natural optimistic algorithm called OFUGLB, applicable to any generalized linear bandits (GLB; Filippi et al. (2010)). Our analysis shows that the celebrated optimistic approach simultaneously attains state-of-the-art regrets for various self-concordant (not necessarily bounded) GLBs, and even $\mathrm{poly}(S)$-free for bounded GLBs, including logistic bandits. The regret analysis, our second technical novelty, follows from combining our new CS with a new proof technique that completely avoids the previously widely used self-concordant control lemma (Faury et al., 2020, Lemma 9). Numerically, OFUGLB outperforms or is at par with prior algorithms for logistic bandits.

stat.ML↗

arXiv2024

Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults

Although gradient descent with Polyak's momentum is widely used in modern machine and deep learning, a concrete understanding of its effects on the training trajectory remains elusive. In this work, we empirically show that for linear diagonal networks and nonlinear neural networks, momentum gradient descent with a large learning rate displays large catapults, driving the iterates towards much flatter minima than those found by gradient descent. We hypothesize that the large catapult is caused by momentum "prolonging" the self-stabilization effect (Damian et al., 2023). We provide theoretical and empirical support for our hypothesis in a simple toy example and empirical evidence supporting our hypothesis for linear diagonal networks.

cs.LG↗

arXiv2024

Querying Easily Flip-flopped Samples for Deep Active Learning

Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. The sample's distance to the decision boundary is a natural measure of predictive uncertainty, but it is often intractable to compute, especially for complex decision boundaries formed in multiclass classification tasks. To address this issue, this paper proposes the {\it least disagree metric} (LDM), defined as the smallest probability of disagreement of the predicted label, and an estimator for LDM proven to be asymptotically consistent under mild assumptions. The estimator is computationally efficient and can be easily implemented for deep learning models using parameter perturbation. The LDM-based active learning is performed by querying unlabeled data with the smallest LDM. Experimental results show that our LDM-based active learning algorithm obtains state-of-the-art overall performance on all considered datasets and deep architectures.

cs.LG↗

arXiv2024

Coarse-grained quantum state tomography with optimal POVM construction

Constructing an integrated large-scale qubit system of realistic size requires addressing the challenge of physical crowding among qubits. This constraint poses an issue of coarse-grained (CG) measurement, wherein information from the multi-qubit system is collectively gathered. In this work, we introduce a novel approach to reconstruct the target density matrix from a comprehensive set of Positive Operator-Valued Measures (POVM) using a Parameterized Quantum Circuit (PQC) under the constraint of CG measurement. We improve the robustness and stability of CG quantum state tomography (QST) by optimizing the POVM set to achieve a generalized symmetric informationally complete (GSIC) POVM through maximization of the von Neumann entropy. This optimized construction of CG-POVMs is scalable to an N-qubit system. We further discuss a more efficient construction of N-qubit CG-QST without exponential increases in two-qubit gates or circuit depth per measurement. Our scheme offers a viable pathway towards a detector-efficient large-scale solid-state embedded qubit platform by reconstructing crucial quantum information from collective measurements.

quant-ph↗

arXiv2024

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion

Logistic bandit is a ubiquitous framework of modeling users' choices, e.g., click vs. no click for advertisement recommender system. We observe that the prior works overlook or neglect dependencies in $S \geq \lVert θ_\star \rVert_2$, where $θ_\star \in \mathbb{R}^d$ is the unknown parameter vector, which is particularly problematic when $S$ is large, e.g., $S \geq d$. In this work, we improve the dependency on $S$ via a novel approach called {\it regret-to-confidence set conversion (R2CS)}, which allows us to construct a convex confidence set based on only the \textit{existence} of an online learning algorithm with a regret guarantee. Using R2CS, we obtain a strict improvement in the regret bound w.r.t. $S$ in logistic bandits while retaining computational feasibility and the dependence on other factors such as $d$ and $T$. We apply our new confidence set to the regret analyses of logistic bandits with a new martingale concentration step that circumvents an additional factor of $S$. We then extend this analysis to multinomial logistic bandits and obtain similar improvements in the regret, showing the efficacy of R2CS. While we applied R2CS to the (multinomial) logistic model, R2CS is a generic approach for developing confidence sets that can be used for various models, which can be of independent interest.

stat.ML↗

arXiv2024

Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks

Multi-armed bandits are extensively used to model sequential decision-making, making them ubiquitous in many real-life applications such as online recommender systems and wireless networking. We consider a multi-agent setting where each agent solves their own bandit instance endowed with a different set of arms. Their goal is to minimize their group regret while collaborating via some communication protocol over a given network. Previous literature on this problem only considered arm heterogeneity and networked agents separately. In this work, we introduce a setting that encompasses both features. For this novel setting, we first provide a rigorous regret analysis for a standard flooding protocol combined with the classic UCB policy. Then, to mitigate the issue of high communication costs incurred by flooding in complex networks, we propose a new protocol called Flooding with Absorption (FwA). We provide a theoretical analysis of the resulting regret bound and discuss the advantages of using FwA over flooding. Lastly, we experimentally verify on various scenarios, including dynamic networks, that FwA leads to significantly lower communication costs despite minimal regret performance loss compared to other network protocols.

cs.LG↗

arXiv2023

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

Fair Principal Component Analysis (PCA) is a problem setting where we aim to perform PCA while making the resulting representation fair in that the projected distributions, conditional on the sensitive attributes, match one another. However, existing approaches to fair PCA have two main problems: theoretically, there has been no statistical foundation of fair PCA in terms of learnability; practically, limited memory prevents us from using existing approaches, as they explicitly rely on full access to the entire data. On the theoretical side, we rigorously formulate fair PCA using a new notion called \emph{probably approximately fair and optimal} (PAFO) learnability. On the practical side, motivated by recent advances in streaming algorithms for addressing memory limitation, we propose a new setting called \emph{fair streaming PCA} along with a memory-efficient algorithm, fair noisy power method (FNPM). We then provide its {\it statistical} guarantee in terms of PAFO-learnability, which is the first of its kind in fair PCA literature. Lastly, we verify the efficacy and memory efficiency of our algorithm on real-world datasets.

stat.ML↗

arXiv2023

Dressed-state control of effective dipolar interaction between strongly-coupled solid-state spins

Strong interactions between spins in many-body solid-state quantum system is a crucial resource for exploring and applying non-classical states. In particular, electronic spins associated with defects in diamond system are a leading platform for the study of collective quantum phenomena and for quantum technology applications. While such solid-state quantum defect systems have the advantage of scalability and operation under ambient conditions, they face the key challenge of controlling interactions between the defects spins, since the defects are spatially fixed inside the host lattice with relative positions that cannot be well controlled during fabrication. In this work, we present a dressed-state approach to control the effective dipolar coupling between solid-state spins; and then demonstrate this scheme experimentally using two strongly-coupled nitrogen vacancy (NV) centers in diamond. Including Rabi driving terms between the m$_s$ = 0 and $\pm$1 states in the NV spin Hamiltonian allows us to turn on and off or tune the effective dipolar coupling between two NV spins. Through Ramsey spectroscopy, we detect the change of the effective dipolar field generated by the control NV spin prepared in different dressed states. To observe the change of interaction dynamics, we then deploy spin-lock-based polarization transfer measurements via a Hartmann-Hahn matching condition between two NV spins in different dressed states. We perform simulations that indicate the promise for this robust scheme to control the distribution of interaction strengths in strongly-interacting spin systems, including interaction strength homogenization in a spin ensemble, which can be a valuable tool for studying non-equilibrium quantum phases and generating high fidelity multi-spin correlated states for quantum-enhanced sensing.

quant-ph↗

arXiv2023

Nearly Optimal Latent State Decoding in Block MDPs

We investigate the problems of model estimation and reward-free learning in episodic Block MDPs. In these MDPs, the decision maker has access to rich observations or contexts generated from a small number of latent states. We are first interested in estimating the latent state decoding function (the mapping from the observations to latent states) based on data generated under a fixed behavior policy. We derive an information-theoretical lower bound on the error rate for estimating this function and present an algorithm approaching this fundamental limit. In turn, our algorithm also provides estimates of all the components of the MDP. We then study the problem of learning near-optimal policies in the reward-free framework. Based on our efficient model estimation algorithm, we show that we can infer a policy converging (as the number of collected samples grows large) to the optimal policy at the best possible rate. Interestingly, our analysis provides necessary and sufficient conditions under which exploiting the block structure yields improvements in the sample complexity for identifying near-optimal policies. When these conditions are met, the sample complexity in the minimax reward-free setting is improved by a multiplicative factor $n$, where $n$ is the number of possible contexts.

cs.LG↗

arXiv2022

Controllable tunability of a Chern number within the electronic-nuclear spin system in diamond

Chern numbers are gaining traction as they characterize topological phases in various physical systems. However, the resilience of the system topology to external perturbations makes it challenging to experimentally investigate transitions between different phases. In this study, we demonstrate the transitions of Chern number from 0 to 3, synthesized in an electronic-nuclear spin system associated with the nitrogen-vacancy (NV) centre in diamond. The Chern number is characterized by the number of degeneracies enclosed in a control Hamiltonian parameter sphere. The topological transitions between different phases are depicted by varying the radius and offset of the sphere. We show that the measured topological phase diagram is not only consistent with the numerical calculations but can also be mapped onto an interacting three-qubit system. The NV system may also allow access to even higher Chern numbers, which can be applied to exploring exotic topology or topological quantum information.

quant-ph↗

arXiv2022

Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold

This paper defines fair principal component analysis (PCA) as minimizing the maximum mean discrepancy (MMD) between dimensionality-reduced conditional distributions of different protected classes. The incorporation of MMD naturally leads to an exact and tractable mathematical formulation of fairness with good statistical properties. We formulate the problem of fair PCA subject to MMD constraints as a non-convex optimization over the Stiefel manifold and solve it using the Riemannian Exact Penalty Method with Smoothing (REPMS; Liu and Boumal, 2019). Importantly, we provide local optimality guarantees and explicitly show the theoretical effect of each hyperparameter in practical settings, extending previous results. Experimental comparisons based on synthetic and UCI datasets show that our approach outperforms prior work in explained variance, fairness, and runtime.

stat.ML↗

arXiv2021

Sub-10 nm precision engineering of solid-state defects via nanoscale aperture array mask

Engineering a strongly interacting uniform qubit cluster would be a major step towards realizing a scalable quantum system for quantum sensing, and a node-based qubit register. For a solid-state system that uses a defect as a qubit, various methods to precisely position defects have been developed, yet the large-scale fabrication of qubits within the strong coupling regime at room temperature continues to be a challenge. In this work, we generate nitrogen vacancy (NV) color centers in diamond with sub-10 nm scale precision by using a combination of nanoscale aperture arrays (NAAs) with a high aspect ratio of 10 and a secondary E-beam hole pattern used as an ion-blocking mask. We perform optical and spin measurements on a small cluster of NV spins and statistically investigate the effect of the NAAs during an ion-implantation process. We discuss how this technique is effective for constructing a scalable system.

quant-ph↗

arXiv2021

Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Data

Homomorphic encryption is one of the representative solutions to privacy-preserving machine learning (PPML) classification enabling the server to classify private data of clients while guaranteeing privacy. This work focuses on PPML using word-wise fully homomorphic encryption (FHE). In order to implement deep learning on word-wise homomorphic encryption (HE), the ReLU and max-pooling functions should be approximated by some polynomials for homomorphic operations. Most of the previous studies focus on HE-friendly networks, where the ReLU and max-pooling functions are approximated using low-degree polynomials. However, for the classification of the CIFAR-10 dataset, using a low-degree polynomial requires designing a new deep learning model and training. In addition, this approximation by low-degree polynomials cannot support deeper neural networks due to large approximation errors. Thus, we propose a precise polynomial approximation technique for the ReLU and max-pooling functions. Precise approximation using a single polynomial requires an exponentially high-degree polynomial, which results in a significant number of non-scalar multiplications. Thus, we propose a method to approximate the ReLU and max-pooling functions accurately using a composition of minimax approximate polynomials of small degrees. If we replace the ReLU and max-pooling functions with the proposed approximate polynomials, well-studied deep learning models such as ResNet and VGGNet can still be used without further modification for PPML on FHE. Even pre-trained parameters can be used without retraining. We approximate the ReLU and max-pooling functions in the ResNet-152 using the composition of minimax approximate polynomials of degrees 15, 27, and 29. Then, we succeed in classifying the plaintext ImageNet dataset with 77.52% accuracy, which is very close to the original model accuracy of 78.31%.

cs.CR↗

arXiv2021

Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network

Fully homomorphic encryption (FHE) is one of the prospective tools for privacypreserving machine learning (PPML), and several PPML models have been proposed based on various FHE schemes and approaches. Although the FHE schemes are known as suitable tools to implement PPML models, previous PPML models on FHE encrypted data are limited to only simple and non-standard types of machine learning models. These non-standard machine learning models are not proven efficient and accurate with more practical and advanced datasets. Previous PPML schemes replace non-arithmetic activation functions with simple arithmetic functions instead of adopting approximation methods and do not use bootstrapping, which enables continuous homomorphic evaluations. Thus, they could not use standard activation functions and could not employ a large number of layers. The maximum classification accuracy of the existing PPML model with the FHE for the CIFAR-10 dataset was only 77% until now. In this work, we firstly implement the standard ResNet-20 model with the RNS-CKKS FHE with bootstrapping and verify the implemented model with the CIFAR-10 dataset and the plaintext model parameters. Instead of replacing the non-arithmetic functions with the simple arithmetic function, we use state-of-the-art approximation methods to evaluate these non-arithmetic functions, such as the ReLU, with sufficient precision [1]. Further, for the first time, we use the bootstrapping technique of the RNS-CKKS scheme in the proposed model, which enables us to evaluate a deep learning model on the encrypted data. We numerically verify that the proposed model with the CIFAR-10 dataset shows 98.67% identical results to the original ResNet-20 model with non-encrypted data. The classification accuracy of the proposed model is 90.67%, which is pretty close to that of the original ResNet-20 CNN model...

cs.LG↗

arXiv2021

High resolution, High contrast optical interface for defect qubits

Point defects in crystals provide important building blocks for quantum applications. To initialize, control, and read-out their quantum states, an efficient optical interface for addressing defects with photons is required. However, conventional confocal fluorescence microscopy with high refractive index crystals has limited photon collection efficiency and spatial resolution. Here, we demonstrate high resolution, high contrast imaging for defects qubits using microsphere-assisted confocal microscopy. A microsphere provides an excellent optical interface for point defects with a magnified virtual image that improves spatial resolution up to ~$λ$/5 as well as an optical signal-to-noise ratio by four times. These features enable individual optical addressing of single photons and single spins of spatially-unresolved defects in conventional confocal microscopy with improved signal contrast. The combined optical tweezers show the possibility of positioning or scanning the microspheres for deterministic coupling and wide-field imaging of defects. The approach does not require any complicated fabrication and additional optical system but uses simple micro-optics off-the-shelf. From these distinctive advantages of the microspheres, our approach can provide an efficient way for imaging and addressing closely-spaced defects with higher resolution and sensitivity.

quant-ph↗

arXiv2020

Unsupervised CT Metal Artifact Learning using Attention-guided beta-CycleGAN

Metal artifact reduction (MAR) is one of the most important research topics in computed tomography (CT). With the advance of deep learning technology for image reconstruction,various deep learning methods have been also suggested for metal artifact removal, among which supervised learning methods are most popular. However, matched non-metal and metal image pairs are difficult to obtain in real CT acquisition. Recently, a promising unsupervised learning for MAR was proposed using feature disentanglement, but the resulting network architecture is complication and difficult to handle large size clinical images. To address this, here we propose a much simpler and much effective unsupervised MAR method for CT. The proposed method is based on a novel beta-cycleGAN architecture derived from the optimal transport theory for appropriate feature space disentanglement. Another important contribution is to show that attention mechanism is the key element to effectively remove the metal artifacts. Specifically, by adding the convolutional block attention module (CBAM) layers with a proper disentanglement parameter, experimental results confirm that we can get more improved MAR that preserves the detailed texture of the original image.

eess.IV↗