Searcharxiv⌕ Search

arXiv subjects

Hao Qin

Publications and source records attributed to Hao Qin.

At least 19 recordsLinked to original sources

A Geometric Perspective for Marginal R2: Estimation and Inference in Generalized Linear Mixed Models

Generalized linear mixed models (GLMMs) are widely used across scientific disciplines, yet quantifying response variation explained by auxiliary information remains challenging for non-Gaussian outcomes and hierarchical dependence. Existing $R^2$ measures provide useful summaries, but their variance-based constructions are not generally linked to a common geometric interpretation, a fixed-design marginal estimand, and corresponding statistical inference. We propose marginal quasi-$R^2$ through two distinct operations. First, marginalization integrates over latent random effects, retaining their uncertainty in the marginal response moments and specifying the model for explanatory assessment. Second, a Quasi-GLM formulation supplies a local working information metric under which orthogonal projection yields an Pythagorean decomposition of explained and unexplained variation. We define a fixed-design population estimand, establish consistency and asymptotic normality of its estimator, and derive cluster-robust sandwich standard errors and confidence intervals under stated regularity conditions. Simulations assess estimation accuracy and interval coverage across response families and random-effects structures. Two ecological applications illustrate the importance of reporting estimation uncertainty alongside marginal quasi-$R^2$. The method is implemented in the R package quasiR2.

stat.ME↗

Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling

We study the problem of $K$-armed bandits with reward distributions belonging to a one-parameter exponential distribution family. In the literature, several criteria have been proposed to evaluate the performance of such algorithms, including Asymptotic Optimality, Minimax Optimality, Sub-UCB, and variance-adaptive regret bound. Thompson Sampling-based and Upper Confidence Bound-based algorithms have been employed to achieve some of these criteria. However, none of these algorithms simultaneously satisfy all the aforementioned criteria. In this paper, we design an algorithm, Exponential Kullback-LeiblerMaillard Sampling (abbrev. Exp-KL-MS), that achieves multiple optimality criteria simultaneously, including Asymptotic Optimality, minimax ratio with a $\sqrt{\ln (K)}$ factor, Sub-UCB, and a variance-adaptive regret bound. Our algorithm design follows the Minimum Empirical Divergence framework~\citep{honda2011asymptotically,maillard2011apprentissage}, with the exploration probability of arm $a$ proportional to $\text{exp}\left(-L(N_{t-1, a}) \text{KL}(\hatμ_{t-1, a}, \max_{a'} \hatμ_{t-1, a'})\right)$, where $L(\cdot)$ is an inverse temperature function, $N_{t-1, a}$ is the number of times arm $a$ has been pulled before time $t$, $\hatμ_{t-1, a}$ is the empirical mean of arm $a$ before time $t$, and $\text{KL}(\cdot, \cdot)$ is the Kullback-Leibler divergence between two distributions in the one-parameter exponential distribution family. Our analysis allows different choices of inverse temperature function $L(k)$. We also provide numerical simulations demonstrating the effectiveness of our algorithms.

cs.LG↗

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

We study the contextual combinatorial semi-bandit (CCSB) problem, where at each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; its goal is to maximize its cumulative reward over time. While many previous works focus on CCSB problems with linear reward function approximation, the design of efficient algorithms for the CCSB problem with general reward function approximation is limited. In this work, we study the realizable setting where the learner has access to a reward function class $\mathcal{F}$ that contains the true reward function, and propose the $\mathrm{SquareCB{.}Comb}$ algorithm. We prove that $\mathrm{SquareCB{.}Comb}$ achieves a minimax optimal regret bound of $O(\sqrt{m A T \log |\mathcal{F}|})$, where $A$ is the number of arms, $m$ is the maximum number of arms in a combinatorial action, and $T$ is the time horizon. In addition, $\mathrm{SquareCB{.}Comb}$ is computationally efficient when we have an online regression oracle that can efficiently predict rewards of all arms given contexts, and the combinatorial action set admits either efficient linear optimization or efficient sampling given any target marginal probability on arms. We empirically verify the effectiveness of our algorithm in webpage recommendation and contextual shortest path problems.

cs.LG↗

Efficient contextual partial monitoring with general function approximation

We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round $t \in [T]$, both player and environment observe a context and player chooses an action and environment simultaneously chooses an outcome. The player neither observes the outcome nor the loss; instead, they only observe a feedback symbol which is partially informative about the outcome. We utilize the Estimation-to-Decisions (E2D) meta-algorithm of Foster et al.(2021) to design E2D.PMSide, a computationally efficient framework for contextual partial monitoring, which uses an online regression oracle to efficiently estimate the outcome distributions based on historical (context, action, feedback symbol) tuples. Since the exploration rule given by the original E2D algorithm is intractable to compute, we propose two computationally efficient exploration rules that achieve optimal regret orders in $T$: in the globally observable setting, our exploration rule is based on $ε$-greedy, while in the locally observable setting, our exploration rule uses inverse gap weighting (Foster & Rakhlin, 2020), which was previously only known to be effective in the bandit setting. We show that a variant of E2D.PMSide named OE2D.PMSide can be combined with offline regression oracles to give an efficient algorithm with optimal regret when the contexts are drawn independently from a fixed distribution. We evaluate our algorithm on a synthetic label-efficient prediction game and an LLM routing task, in which a learner decides from prompt, uncertainty, and internal state features whether to escalate a query from a weak model to a strong one. We show that our method has superior performance to prior approaches.

cs.LG↗

From Electromagnetic Physics to Intelligent Optimization: A Deterministic Modeling for Indoor Pinching-Antenna Systems

Pinching-antenna systems (PASS) enable flexible wireless transmission by activating pinching antennas (PAs) along dielectric waveguides. However, existing PASS analyses commonly rely on tractable analytical or statistical channel abstractions that do not jointly capture in-waveguide field evolution, sequential PA power extraction, and site-specific indoor multipath propagation. This paper develops a physics-driven deterministic framework for end-to-end modeling of indoor PASS. Specifically, the parabolic wave equation (PWE) resolves the position-dependent electromagnetic field inside the dielectric waveguide, and coupled-mode theory (CMT) maps the local guided field to the radiation power and phase of each PA. Ray tracing (RT) subsequently models the site-specific indoor electromagnetic propagation from each PA to the users, including LoS, reflected, and diffracted components. To enable efficient repeated evaluations, we combine a reusable PWE-CMT field representation with a physics-assisted neural-network-based RT surrogate that preserves propagation geometry, visibility, and phase information. The proposed framework achieves a complex-channel NMSE of -19.14 dB while reducing the end-to-end single-link evaluation time from approximately 2.5 s to 77 ms. Its application to single- and multi-user deployment demonstrates that the physical model can be efficiently reused for PA-position and power-allocation optimization while preserving the underlying position-dependent propagation physics.

eess.SP↗

More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses

Automated generation of LLM harnesses promises to improve inference through task specialization. Yet additional answer coverage can arise from repeated execution of the same program, making specialization difficult to identify. We introduce a controlled evaluation that separates answer coverage, repeatable task advantages, and gains from pre-execution selection. On 386 MATH-500 tasks, we compare eight generated harnesses plus a baseline with nine byte-identical baseline copies, using three executions per member. Identical programs yield 2.16 percentage points of repeat-averaged oracle headroom. Generated programs exhibit substantially more repeatable score patterns, but these chiefly reveal persistent weaknesses: losses relative to the baseline persist across all three repeats on 100 tasks, while persistent wins occur on only one task and are sensitive to answer extraction. The frozen selector gains 0.00 percentage points, and both populations reach 98.70% oracle coverage at 27 harness executions. Stable complementarity remains unresolved at three repeats. Supporting BIRD traces locate failures in mechanism implementation, activation, and output validity. Together, these findings establish why coverage and repeatability alone cannot justify claims of useful specialization. They motivate an evaluation standard for harness diversity: task advantages should persist across executions, guide usable decisions, and improve on additional fixed-program executions under matched inference budgets.

cs.AI↗

Adaptive Polynomial Chaos Expansion for Uncertainty Quantification of Radio Wave Propagation over Irregular Terrains

Accurate modeling of radio wave propagation over irregular terrains is crucial for designing reliable wireless communication systems in such environments, yet uncertainties in the antenna configuration are not quantified within deterministic models. This paper develops a fixed number of samples adaptive polynomial chaos expansion (APCE) method for uncertainty quantification (UQ) of radio wave propagation over realistic irregular terrains, where the model evaluations are obtained using a two-way parabolic wave equation (PWE) method. The proposed APCE method is designed to construct a compact and stable PCE model from a prescribed and limited set of simulations. The polynomial basis is enriched using an anisotropic basis extension algorithm driven by variance contributions, while validation behavior and the available sample size are used to control basis growth. The convergence analysis shows decreasing validation errors and improved robustness as the sampling budget increases, with lower trial-to-trial variability than the baseline adaptive PCE method, which uses the same variance-driven basis extension strategy. For two realistic terrain profiles, the proposed method accurately predicts the mean and the 5-95 percentile range of the path loss, and improves the estimation of the standard deviation compared with standard and sparse PCE, using only 30 PWE simulations. APCE outperforms standard and sparse PCE, with the largest gains observed for the 5th and 95th percentile estimates, and its construction time is close to that of standard PCE and much lower than that of sparse PCE based on least angle regression. As the sample size increases, APCE maintains low errors with reduced trial-to-trial variability.

eess.SP↗

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Together, these compute, storage, and bandwidth demands constitute the primary bottleneck to further lowering deployment costs. To address this challenge, we introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. With its Causal Encoder-Decoder (CED) architecture, the model activates 16B parameters per token during decode but only 8B parameters during prefill, substantially improving cost efficiency for agentic workloads. To push the limits of KV cache compression, DeepSeek-V4.1-Flash combines cross-layer KV cache reuse in Compressed Sparse Attention 2 (CSA2) with FP4 KV caching. These designs reduce its global KV cache footprint (always in HBM) to 890 bytes per token, roughly 1/4 of the corresponding footprint of DeepSeek-V4-Flash. Further, through a dedicated deployment optimization known as SWA Bounded Replay, DeepSeek-V4.1-Flash reduces its persistent KV cache footprint (always on SSD or in host memory) to roughly 1/8 of that of DeepSeek-V4-Flash. Despite its much smaller KV cache footprint, the model delivers substantially better performance than the baseline. In addition, we streamline the DeepSeek-V4 architecture and introduce several efficient architectural extensions. We pretrain DeepSeek-V4.1-Flash on a multimodal corpus comprising 45T tokens and conduct comprehensive post-training, yielding strong performance across diverse text-based and multimodal agentic scenarios. Model checkpoints are available at https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash.

cs.CL↗

NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting

With the rapid development and adoption of 3D Gaussian Splatting (3DGS), the need for effective copyright protection has become increasingly critical. Existing watermarking techniques for 3DGS mainly focus on protecting rendered images via pre-trained decoders, leaving the underlying 3D Gaussian primitives vulnerable to misuse. In particular, they are ineffective against Partial Infringement, where an adversary extracts and reuses only a subset of Gaussians. In this paper, we propose NGS-Marker, a novel native watermarking framework for 3DGS. It integrates a jointly trained watermark injector and message decoder, and employs a gradientbased progressive injection strategy to ensure full-scene coverage. This enables robust ownership decoding from any local region. We further extend NGS-Marker with hybrid protection (combining native and indirect watermarks) and support for multimodal watermarking. Extensive experiments demonstrate that NGS-Marker effectively defends against partial infringement while offering practical flexibility for real-world deployment.

cs.CV↗

Learning Graph-Indexed Trajectory Patterns for Stochastic On-Time Arrival Routing

Correlated link travel times create decision-relevant patterns in partial route histories. In stochastic on-time arrival (SOTA) routing, each route prefix forms a variable-length, graph-indexed sequence in which traversed-edge identities, realized travel times, and route order jointly indicate the reliability of downstream actions. We present GPG-HT, a history-conditioned Transformer policy that learns a trajectory representation from this structured sequence together with the current node, destination, and remaining budget. Edge-time cross-attention and sequence encoding capture dependencies within the observed history, while decoder cross-attention maps the resulting trajectory memory and decision context to an online distribution over feasible outgoing edges. A history-conditioned generalized policy-gradient objective trains the representation from terminal on-time outcomes. Experiments on the Sioux Falls and Anaheim road-network topologies with simulated correlated link times show that GPG-HT achieves higher mean on-time arrival probabilities than representative optimization and reinforcement-learning baselines. Paired common-pool evaluation confirms statistically significant gains in all six network-budget settings, reaching 2.82-3.27 percentage points on Sioux Falls and 0.36-1.04 percentage points on Anaheim. Correlated, independent, shuffled-history, no-history, and architecture controls further demonstrate that GPG-HT learns decision-relevant structure from graph-indexed route prefixes.

cs.LG↗

Robust and Fast Bass Local Volatility

The Bass Local Volatility Model, as studied in {henry2021bass}, stands out for its ability to eliminate the need for interpolation between maturities. This offers a significant advantage over traditional local volatility models. However, its performance highly depends on accurate construction of risk neutral densities and the corresponding marginal distributions and efficient numerical convolutions which are necessary when solving the associated fixed point problems. In this paper, we propose a new approach combining local quadratic estimation and lognormal mixture tails for the construction of risk neutral densities. We investigate computational efficiency of trapezoidal rule based schemes for numerical convolutions and show that they outperform commonly used Gauss-Hermite quadrature. We demonstrate the performance of the proposed method, both in standard option pricing models, as well as through a detailed market case study.

q-fin.CP↗

Arbitrage-Free Multi-Maturity Risk-Neutral Marginals

Many quantitative finance methods and applications are formulated in terms of option-implied risk-neutral marginals rather than directly in terms of option prices. Representative examples include martingale optimal transport, Bass local-volatility calibration, scenario analysis, and option-implied tail-risk measurement. The desired risk-neutral marginals should define a genuine probability law on the entire support, reproduce the input arbitrage-free option prices exactly, be free of butterfly and calendar arbitrage, and admit efficient evaluation of the density, distribution function, and quantiles, as well as Monte Carlo sampling. Existing methods typically optimize only a subset of these properties, depending on their intended purpose. This leaves a gap between upstream arbitrage-free option prices and the readily usable risk-neutral marginals required by downstream applications. We propose an explicit construction of risk-neutral marginals from discrete arbitrage-free option prices. On the observed strike range, probability mass is assigned interval by interval to exactly reproduce the input option prices. Outside the observed range, closed-form power-law tails complete the distribution by satisfying price and slope boundary conditions and allocating the remaining probability mass. Butterfly- and calendar-arbitrage-freeness are guaranteed by construction. The construction is feasible by design and computationally efficient. The resulting marginal laws admit closed-form densities, distribution functions, quantiles, and efficient Monte Carlo sampling. Numerical experiments on synthetic SSVI data and S\&P~500 market data demonstrate that the proposed construction efficiently and robustly produces marginals satisfying all of these properties in practice.

q-fin.CP↗

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual bandits with large action spaces with $O(\log T)$ calls to an offline regression oracle over $T$ rounds, and makes $O(\log\log T)$ calls when $T$ is known. The design of OE2D algorithm generalizes Falcon~\citep{simchi2022bypassing} and its linear reward version~\citep[][Section 4]{xu2020upper} in that it finds an action distribution that we term ``exploitative F-design'' that simultaneously guarantees low regret and good coverage, striking a balance between exploration and exploitation. Central to our regret analysis is a new complexity measure, the Decision-Offline Estimation Coefficient (DOEC), which we show is small in many settings, including bounded Eluder dimension per-context and the smoothed regret setting. We also establish a relationship between DOEC and Decision Estimation Coefficient (DEC)~\citep{foster2021statistical}, bridging the design principles of offline- and online-oracle efficient contextual bandit algorithms for the first time.

cs.LG↗

Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness. We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks, where early detections are converted into spatial prompts via a Point-Line Prompt Encoder (PLP-Encoder), which encodes geometric attributes into compact and spatially aligned maps. A Cross-Guidance Line Decoder (CGL-Decoder) then refines predictions with sparse attention conditioned on complementary prompts, enforcing point-line consistency and efficiency. Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency, demonstrating our effectiveness for structured geometry perception. Our code is available at https://github.com/GalacticHogrider/Co-PLNet.

cs.CV↗

Spatio-Sequential Recurrent Network for 3-D Tunnel Propagation Modeling

Fine-mesh parabolic wave equation (PWE) simulations are high-fidelity but time-consuming, which limits real-time tunnel propagation analysis and motivates coarse-to-fine reconstruction. Existing machine learning (ML)-assisted tunnel models typically provide only one-dimensional (1-D) longitudinal refinement or two-dimensional (2-D) cross-sectional refinement, rather than joint 3-D enhancement. Motivated by this gap, this letter proposes a U-shaped gated spatio-sequential recurrent neural network (UG-SSRNN), a spatio-sequential reconstruction model for tunnel electromagnetic fields. UG-SSRNN jointly super-resolves transverse slices and models longitudinal evolution. It uses sliding-window context encoding and a K-layer convolutional recurrent backbone with a shared propagation-context state and diagonal feedback. A prediction-aware upsampling head leverages the previous prediction to improve slice-to-slice consistency. Experiments on four tunnel cross sections, unseen-material and unseen-frequency tests, and validation in the Massif Central tunnel show close agreement with fine-mesh PWE references. The proposed approach significantly reduces tunnel electromagnetic modeling time.

eess.SP↗

Real-Space Imaging of Guided Exciton Polaritons in Free-standing Monolayer WSe2

Monolayers of transition metal dichalcogenides (TMDCs), known for their strong excitonic states with high binding energies in the visible spectrum at room temperature, offer great potential for polariton-driven devices. While polariton guided modes in bulk TMDCs have been reported the real space experimental observation of 2D exciton-polariton guided modes in a monolayer remains challenging due to various mode cut-off conditions that arise as the TMDC layer becomes thinner, including cut-off frequency, mode confinement and boundary conditions. Here using scanning near-field optical microscopy (s-SNOM), we directly visualized the real-space propagation of these guided modes for the first time in an angstrom-thick, suspended monolayer of WSe2. Through numerical simulations we have also validated that the guided mode can only exist in a monolayer WSe2 when symmetric cladding conditions are closely applied. By tuning the excitation laser energy and analysing the guided mode distribution, we observed a pronounced back-bending dispersion around the A exciton, indicating strong light-matter interactions, and confirmed the existence of the fundamental TE0 exciton polariton (EP) propagation mode. The unique dispersion characteristics of these modes were further validated through theoretical modelling of the mode in free-standing monolayer WSe2. Our findings provide crucial experimental evidence of guided mode EPs in atomically thin TMDCs, opening new possibilities for nanoscale photonic applications.

physics.optics↗

AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents

The rapid development of AI agent systems is leading to an emerging Internet of Agents, where specialized agents operate across local devices, edge nodes, private services, and cloud platforms. Although recent efforts have improved agent naming, discovery, and interaction, efficient request dispatch remains an open systems problem under latency, privacy, and cost constraints. In this paper, we present AgentGate, a lightweight structured routing engine for candidate-aware agent dispatch. Instead of treating routing as unrestricted text generation, AgentGate formulates it as a constrained decision problem and decomposes it into two stages: action decision and structural grounding. The first stage determines whether a query should trigger single-agent invocation, multi-agent planning, direct response, or safe escalation, while the second stage instantiates the selected action into executable outputs such as target agents, structured arguments, or multi-step plans. To adapt compact models to this setting, we further develop a routing-oriented fine-tuning scheme with candidate-aware supervision and hard negative examples. Experiments on a curated routing benchmark with several 3B--7B open-weight models show that compact models can provide competitive routing performance in constrained settings, and that model differences are mainly reflected in action prediction, candidate selection, and structured grounding quality. These results indicate that structured routing is a feasible design point for efficient and privacy-aware agent systems, especially when routing decisions must be made under resource-constrained deployment conditions.

cs.AI↗

MSSSeg: Learning Multi-Scale Structural Complexity for Self-Supervised Segmentation

Self-supervised semantic segmentation methods often suffer from structural errors, including merging distinct objects or fragmenting coherent regions, because they rely primarily on low-level appearance cues such as color and texture. These cues lack structural discriminability: they carry no information about the structural organization of a region, making it difficult to distinguish boundaries between similar-looking objects or maintain coherence within internally varying regions. Recent approaches attempt to address this by incorporating depth priors, yet remain limited by not explicitly modeling structural complexity that persists even when appearance cues are ambiguous. To bridge this gap, we present MSSSeg, a framework that explicitly learns multi-scale structural complexity from both semantic and depth domains, via three coupled components: (1) a Differentiable Box-Counting (DBC) module that captures and aligns multi-scale structural complexity features with semantic features; (2) a Learnable Structural Augmentation (StructAug) that corrupts pixel-intensity patterns, forcing the network to rely on structural complexity features from DBC; and (3) a Persistent Homology Loss (PHLoss) that directly supervises the structural complexity of predicted segmentations. Extensive experiments demonstrate that MSSSeg achieves new state-of-the-art performance on COCO-Stuff-27, Cityscapes, and Potsdam without excessive computational overhead, validating that explicit structural complexity learning is crucial for self-supervised segmentation.

cs.CV↗