arXiv subjects

Nam Nguyen

Publications and source records attributed to Nam Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments

We propose Variance Driven Exploration (VarDE), a principled approach for pure exploration in highly stochastic environments, where the exploration process is dominated by stochastic variance. VarDE is built on a fundamental principle: sampling effort should be allocated to minimize the uncertainty of the final decision. We formalize the uncertainty of the final decision through a smooth decision function and derive allocation rules that explicitly capture how stochastic noise in individual components affects the reliability of the final output. We apply this methodology to three core problems of pure exploration -- Best Arm Identification (BAI), Monte Carlo Tree Search (MCTS), and Best-Policy Identification (BPI) -- with theoretical guarantees on variance decay and simple regret. Empirically, we demonstrate consistent and significant improvements of VarDE over existing methods, with especially strong gains in highly stochastic environments.

cs.LG↗

arXiv2026

Preservation of Positive-Definiteness by Bernstein Operators on the Circle

We prove that, for every $n\ge1$, the degree-$n$ Bernstein operator on $[0,\pi]$ preserves positive-definiteness on the circle $S^1$. Equivalently, if a continuous function on $[0,\pi]$ defines a positive-definite isotropic kernel on $S^1$, then its Bernstein polynomial approximation of any fixed degree does as well. The proof reduces the problem to the nonnegativity of the cosine coefficients of the Bernstein images $Q_{n,m}=B_n[\cos(mx)]$, which we prove using an explicit coefficient formula and a two-regime positivity argument. We also discuss the higher-dimensional sphere analogue and show that the naive affine Bernstein operator fails to preserve the positive-definite cone already on $S^2$.

math.CA↗

arXiv2026

Conservation Laws for Modern Neural Architectures

Understanding gradient descent dynamics is key to explaining the success of over-parameterized models, where implicit bias manifests through conservation laws in gradient flow. While such laws are well understood for linear and ReLU networks, they remain largely unexplored for modern architectures. This work develops a unified framework to characterize conservation laws for contemporary models, including feedforward networks with GELU, SiLU, and SwiGLU activations, multihead attention with sinusoidal and rotary positional encodings, and Mixture-of-Experts architectures under diverse gating designs. Our theoretical findings are supported by experiments that validate the predicted invariants.

cs.LG↗

arXiv2026

Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis

Quadratic regularization has emerged as a potential alternative to the popular entropic regularization in computational optimal transport, offering the theoretical advantage of producing sparse couplings through its hinge density structure. Despite recent progress in one-dimensional settings and general upper bounds, fundamental questions about the localization rate of QOT optimizers around the Monge coupling have remained open. In this work, we establish a general lower bound showing that the support of the QOT optimizer cannot concentrate around the Monge graph faster than order $\varepsilon^{\frac{1}{d+2}}$ in the directed Hausdorff distance, matching the conjectured optimal exponent under standard regularity assumptions in \citet{wiesel2025sparsity}. We also show that the QOT value gap controls the mean-squared deviation $\mathbb E_{\pi_\varepsilon}\|y-T(x)\|^2$ by the scale of $\varepsilon^{\frac{2}{d+2}}$. As a corollary, in the affine Brenier regime, which includes Gaussian-to-Gaussian transport, we derive a sharp pointwise tube bound of order $\varepsilon^{\frac{1}{d+2}}$ by reducing the problem to self-transport and applying recent self-transport sparsity results. Finally, we validate our theoretical bound with a synthetic experiment in high-dimensional settings.

math.OC↗

arXiv2026

Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling

This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is required to generate outputs following a prescribed target distribution and to preserve information relevant to a downstream classification task. Motivated by logarithmic-loss distortion, we adopt an information-based objective that maximizes the coupling strength between the source and reconstruction, rather than minimizing a sample-wise distortion. Under common randomness, we formulate a rate-constrained MEC problem (MEC-B) and show that the intermediate representation can be removed without loss of optimality, yielding an equivalent deterministic coupling formulation. For Bernoulli sources, closed-form expressions are derived with and without classification constraints. In addition, we implement a neural restoration framework using quantization, entropy modeling, distribution matching, and classification regularization. Experiments on MNIST super-resolution and SVHN denoising show that increasing the available rate improves classification accuracy and yields more informative reconstructions.

cs.IT↗

arXiv2026

Cooptimizing Safety and Performance Using Safety Value-Constrained Model Predictive Control

Autonomous systems are increasingly deployed in real-world environments, where they must achieve high performance while maintaining safety under state and input constraints. Although Model Predictive Control (MPC) provides a principled framework for constrained optimal control, guaranteeing safety beyond its finite planning horizon remains a fundamental challenge. In this work, we augment MPC with a safety value function-based terminal constraint that enforces membership in a control-invariant safe set at the end of each planning horizon. This formulation enables real-time synthesis of trajectories that are both high-performing and provably safe. We show that, under an exact safety value function and a feasible initialization, the proposed MPC scheme is recursively feasible, thereby ensuring persistent safety. In contrast to traditional terminal set constructions that rely on local linearizations or conservative approximations, our approach incorporates a reachability-based safety value function for terminal constraints, yielding less conservative and more expressive safety guarantees. We validate the proposed framework through simulation and hardware experiments on a Flexiv Rizon 10s manipulator. Results demonstrate improved constraint satisfaction and robustness compared to standard state-constrained MPC and reactive safety filtering, while maintaining competitive task performance. The full implementation and experiments are available on the project website.

cs.RO↗

arXiv2026

Symmetry-based perturbation theory for electronic structure calculations

We develop a multi-reference perturbation theory for electronic structure calculations based on symmetries of the Hamiltonian. The reference Hamiltonian in the symmetry-based perturbation theory (SBPT) is chosen such that it possesses more symmetries than the original Hamiltonian, leading to a larger reduction of computational resources in terms of both the number of configurations in the configuration interaction expansion and the number of required qubits in quantum computing applications. We provide approximate, scalable solutions for the second-order correction, as well as an application to selected configuration interaction. We show that SBPT is an extension of other existing multi-reference perturbation theories and that it can give better results for some molecular systems in a robust way.

quant-ph↗

arXiv2026

Perception-based Image Denoising via Generative Compression

Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution shift. This paper proposes a generative compression framework for perception-based denoising, where restoration is achieved by reconstructing from entropy-coded latent representations that enforce low-complexity structure, while generative decoders recover realistic textures via perceptual measures such as learned perceptual image patch similarity (LPIPS) loss and Wasserstein distance. Two complementary instantiations are introduced: (i) a conditional Wasserstein GAN (WGAN)-based compression denoiser that explicitly controls the rate-distortion-perception (RDP) trade-off, and (ii) a conditional diffusion-based reconstruction strategy that performs iterative denoising guided by compressed latents. We further establish non-asymptotic guarantees for the compression-based maximum-likelihood denoiser under additive Gaussian noise, including bounds on reconstruction error and decoding error probability. Experiments on synthetic and real-noise benchmarks demonstrate consistent perceptual improvements while maintaining competitive distortion performance.

cs.CV↗

arXiv2026

Dissipative continuation for ground-state preparation at chemical transition states

Simulating chemical reactions exhibits a pronounced unevenness in computational difficulty: while equilibrium reactant and product geometries are often tractable, transition-state (TS) geometries frequently display strong multi-reference character that challenges both classical solvers and coherent quantum state-preparation methods. We introduce a dissipative continuation protocol for preparing electronic ground states near TS geometries within a hybrid classical--quantum workflow. In the intended setting, classical electronic-structure methods supply an approximate TS geometry, a computationally motivated continuation path, and a locally compatible active-space representation along that path. Starting from a warm start at a tractable geometry on the same aligned path, the quantum routine transports the state toward the TS using orbital-gauge-aligned Hamiltonians and engineered dissipative cooling primitives that repeatedly contract population into the instantaneous low-energy sector. We prove that, for continuation paths satisfying a Lipschitz smoothness condition and a localized Eigenstate Thermalization Hypothesis (ETH)-motivated downward-drift condition within the relevant energy window, the ground state at the target geometry can be prepared to total energy error $\epsilon_E$ with total ideal cooling-step complexity $\widetilde{O}(C_{\mathrm{DK}}^2 N_o^2 / \epsilon_E)$. Here $C_{\mathrm{DK}}$ quantifies ground-state rotation along the aligned path. The corresponding logical gate count is obtained by multiplying this primitive count by the cost of implementing one dissipative step, which is polynomial in the block-encoding size of the Lindbladian under standard Lindblad-simulation algorithms. This identifies a structured regime in which dissipative continuation provides a conditional route to ground-state preparation at strongly correlated TS geometries.

quant-ph↗

arXiv2026

Rate-Distortion-Classification Representation Theory for Bernoulli Sources

We study task-oriented lossy compression through the lens of rate-distortion-classification (RDC) representations. The source is Bernoulli, the distortion measure is Hamming, and the binary classification variable is coupled to the source via a binary symmetric model. Building on the one-shot common-randomness formulation, we first derive closed-form characterizations of the one-shot RDC and the dual distortion-rate-classification (DRC) tradeoffs. We then use a representation-based viewpoint and characterize the achievable distortion-classification (DC) region induced by a fixed representation by deriving its lower boundary via a linear program. Finally, we study universal encoders that must support a family of DC operating points and derive computable lower and upper bounds on the minimum asymptotic rate required for universality, thereby yielding bounds on the corresponding rate penalty. Numerical examples are provided to illustrate the achievable regions and the resulting universal RDC/DRC curves.

cs.IT↗

arXiv2025

EEG-X: Device-Agnostic and Noise-Robust Foundation Model for EEG

Foundation models for EEG analysis are still in their infancy, limited by two key challenges: (1) variability across datasets caused by differences in recording devices and configurations, and (2) the low signal-to-noise ratio (SNR) of EEG, where brain signals are often buried under artifacts and non-brain sources. To address these challenges, we present EEG-X, a device-agnostic and noise-robust foundation model for EEG representation learning. EEG-X introduces a novel location-based channel embedding that encodes spatial information and improves generalization across domains and tasks by allowing the model to handle varying channel numbers, combinations, and recording lengths. To enhance robustness against noise, EEG-X employs a noise-aware masking and reconstruction strategy in both raw and latent spaces. Unlike previous models that mask and reconstruct raw noisy EEG signals, EEG-X is trained to reconstruct denoised signals obtained through an artifact removal process, ensuring that the learned representations focus on neural activity rather than noise. To further enhance reconstruction-based pretraining, EEG-X introduces a dictionary-inspired convolutional transformation (DiCT) layer that projects signals into a structured feature space before computing reconstruction (MSE) loss, reducing noise sensitivity and capturing frequency- and shape-aware similarities. Experiments on datasets collected from diverse devices show that EEG-X outperforms state-of-the-art methods across multiple downstream EEG tasks and excels in cross-domain settings where pre-trained and downstream datasets differ in electrode layouts. The models and code are available at: https://github.com/Emotiv/EEG-X

cs.LG↗

arXiv2025

End-to-End Complexity Analysis for Quantum Simulation of the Extended Jaynes-Cummings Models

The extended Jaynes-Cummings model (eJCM) is a foundational framework for describing multi-mode light-matter interactions, with direct applications in quantum technologies such as photon addition and quasi-noiseless amplification. However, the model's complexity makes classical simulation intractable for large systems that could be of practical interest. In this work, we present a comprehensive, end-to-end framework for the quantum simulation of the eJCM. We develop explicit quantum algorithms and circuits for simulating the system's time evolution using first and second-order product formulas, analyzing the dynamics in both the Schrodinger and interaction pictures. Our analysis includes rigorous, closed-form error bounds that guide the choice of simulation parameters, and we extend the methodology to efficiently handle both pure and mixed quantum states. Furthermore, we validate our theoretical cost models with numerical simulations and provide a detailed fault-tolerant resource analysis, compiling the simulation circuits for a surface-code architecture to yield concrete estimates for physical qubit counts and execution times. This work establishes a complete roadmap for simulating the eJCM on future quantum computers.

quant-ph↗

arXiv2025

BEDTime: A Unified Benchmark for Automatically Describing Time Series

Recent works propose complex multi-modal models that handle both time series and language, ultimately claiming high performance on complex tasks like time series reasoning and cross-modal question answering. However, they skip foundational evaluations that such complex models should have mastered. So we ask a simple question: \textit{How well can recent models describe structural properties of time series?} To answer this, we propose that successful models should be able to \textit{recognize}, \textit{differentiate}, and \textit{generate} descriptions of univariate time series. We then create \textbf{\benchmark}, a benchmark to assess these novel tasks, that comprises \textbf{five datasets} reformatted across \textbf{three modalities}. In evaluating \textbf{17 state-of-the-art models}, we find that (1) surprisingly, dedicated time series-language models fall short, despite being designed for similar tasks, (2) vision language models are quite capable, (3) language only methods perform worst, despite many lauding their potential, and (4) all approaches are clearly fragile to a range of real world robustness tests, indicating directions for future work. Together, our findings critique prior works' claims and provide avenues for advancing multi-modal time series modeling.

cs.CL↗

arXiv2025

QB Ground State Energy Estimation Benchmark

Ground State Energy Estimation (GSEE) is a central problem in quantum chemistry and condensed matter physics, demanding efficient algorithms to solve complex electronic structure calculations. This work introduces a structured benchmarking framework for evaluating the performance of both classical and quantum solvers on diverse GSEE problem instances. We assess three prominent methods -- Semistochastic Heat-Bath Configuration Interaction (SHCI), Density Matrix Renormalization Group (DMRG), and Double-Factorized Quantum Phase Estimation (DF QPE) -- ighlighting their respective strengths and limitations. Our results show that fully optimized SHCI achieves near-universal solvability on the benchmark set, DMRG excels for low-entanglement systems, and DF QPE is currently constrained by hardware and algorithmic limitations. However, we observe that many benchmark Hamiltonians are drawn from datasets tailored to SHCI and related approaches, introducing a bias that favors classical solvers. To mitigate this, we propose expanding the benchmark suite to include more challenging, strongly correlated systems to enable a more balanced and forward-looking evaluation of solver capabilities. As quantum hardware and algorithms improve, this benchmarking framework will serve as a vital tool for tracking progress and identifying domains where quantum methods may surpass classical techniques. The QB-GSEE benchmark repository is openly available at https://github.com/isi-usc-edu/qb-gsee-benchmark [1]. By maintaining a scalable and open resource, we aim to accelerate innovation in computational quantum chemistry and quantum computing.

quant-ph↗

arXiv2025

Quantum-centric simulation of hydrogen abstraction by sample-based quantum diagonalization and entanglement forging

The simulation of electronic systems is an anticipated application for quantum-centric computers, i.e. heterogeneous architectures where classical and quantum processing units operate in concert. An important application is the computation of radical chain reactions, including those responsible for the photodegradation of composite materials used in aerospace engineering. Here, we compute the activation energy and reaction energy for hydrogen abstraction from 2,2-diphenyldipropane, used as a minimal model for a step in a radical chain reaction. Calculations are performed using a superconducting quantum processor of the IBM Heron family and classical computing resources. To this end, we combine a qubit-reduction technique called entanglement forging (EF) with sample-based quantum diagonalization (SQD), a method that projects the Schr\"{o}dinger equation into a subspace of configurations sampled from a quantum device. In conventional quantum simulations, a qubit represents a spin-orbital. In contrast, EF maps a qubit to a spatial orbital, reducing the required number of qubits by half. We provide a complete derivation and a detailed description of the combined EF and SQD approach, and we assess its accuracy across active spaces of varying sizes upto (39e,39o).

quant-ph↗

arXiv2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

cs.CL↗

arXiv2025

Existence of a robust optimal control process for efficient measurements in a two-qubit system

The verification of quantum entanglement is essential for quality control in quantum communication. In this work, we propose an efficient protocol to directly verify the two-qubit entanglement of a known target state through a single expectation value measurement. Our method provides exact entanglement quantification using the currencence measure without performing quantum state tomography. We prove the existence of a unitary transformation that drives the initial state of a two-qubit system to a designated final state, where the trace over a chosen observable directly yields the concurrence of the initial state. Furthermore, we implement an optimal control process of that transformation and demonstrate its effectiveness through numerical simulations. We also show that this process is robust to environmental noise. Our approach offers advantages in directly verifying entanglement with low circuit depth, making it suitable for industrial-scale quality control of entanglement generation. Our results, presented here, provide mathematical justification for our earlier computational experiments.

quant-ph↗

arXiv2025

VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal

Recent advances in Novel View Synthesis (NVS) and 3D generation have significantly improved editing tasks, with a primary emphasis on maintaining cross-view consistency throughout the generative process. Contemporary methods typically address this challenge using a dual-strategy framework: performing consistent 2D inpainting across all views guided by embedded priors either explicitly in pixel space or implicitly in latent space; and conducting 3D reconstruction with additional consistency guidance. Previous strategies, in particular, often require an initial 3D reconstruction phase to establish geometric structure, introducing considerable computational overhead. Even with the added cost, the resulting reconstruction quality often remains suboptimal. In this paper, we present VEIGAR, a computationally efficient framework that outperforms existing methods without relying on an initial reconstruction phase. VEIGAR leverages a lightweight foundation model to reliably align priors explicitly in the pixel space. In addition, we introduce a novel supervision strategy based on scale-invariant depth loss, which removes the need for traditional scale-and-shift operations in monocular depth regularization. Through extensive experimentation, VEIGAR establishes a new state-of-the-art benchmark in reconstruction quality and cross-view consistency, while achieving a threefold reduction in training time compared to the fastest existing method, highlighting its superior balance of efficiency and effectiveness.

cs.GR↗