arXiv:2601.19041v1 Announce Type: new Abstract: Heatmap-based non-autoregressive solvers for large-scale Travelling Salesman Problems output dense edge-probability scores, yet final performance largely hinges on the decoder that must satisfy degree-2 constraints and form a single Hamiltonian tour. Greedy commitment can cascade into irreparable mistakes at large $N$, whereas MCTS-guided local search is accurate but compute-heavy and highly engineered. We instead treat the heatmap as a soft edge prior and cast decoding as probabilistic tour construction under feasibility constraints, where […]

Ver mais

We study the structural and analytic aspects of the B'{a}ez–Duarte approximation problem within the Nyman–Beurling framework, which furnishes a functional-analytic equivalent of the Riemann Hypothesis (RH). Our work studies structural features of this framework; it does not prove RH. First (Rank-one collapse and Hilbert-space theory). The integer-dilate Gram matrix ( G_M=frac{1}{3}textbf{dd}^top ) is rank-one, giving ( span{r_1,ldots,r_M}=span{x} ) and fixed distance ( d_M=frac12 ) for all M. We give the explicit Moore–Penrose pseudoinverse ( G_M^+ ) and the […]

Ver mais

arXiv:2602.09213v1 Announce Type: new Abstract: Non-contact current monitoring has emerged as a prominent research focus owing to its non-intrusive characteristics and low maintenance requirements. However, while they offer high sensitivity, contactless sensors necessitate sophisticated design methodologies and thorough experimental validation. In this study, a Giant Magneto-Resistance (GMR) sensor is employed to monitor the instantaneous currents of a three-phase 400-volt overhead line, and its performance is evaluated against that of a conventional contact-based Hall effect sensor. A mathematical framework […]

Ver mais

How TITANS Bridges Neuroscience and Machine Learning to Solve the Memory Problem The release of Google’s TITANS architecture in late 2024 marks a theoretical inflection point in how we conceptualize machine memory. This isn’t merely another incremental improvement in long-context processing — it’s a fundamental rethinking of what it means for neural networks to learn, remember, and forget. By implementing principles from cognitive neuroscience that have been validated over six decades, TITANS demonstrates that biological memory systems aren’t just inspiration — they’re a […]

Ver mais

Efficient calibration is essential for the practical application of option pricing models. The Fractional Stochastic Volatility Jump Diffusion (FVSJ) model proposed by Zhang and Yong [1] can reproduce several stylized features observed in option markets, including the volatility smile, volatility clustering, and long-memory effects. However, its multiple stochastic components make conventional calibration computationally expensive. This paper proposes a two-step calibration framework that combines a neural network with a differential evolution (DE) algorithm. In the first step, we construct […]

Ver mais

arXiv:2504.13961v2 Announce Type: replace-cross Abstract: Accurate short-term traffic demand prediction is critical for the operation of traffic systems. Besides point estimation, the confidence interval of the prediction is also of great importance. Many models for traffic operations, such as shared bike rebalancing and taxi dispatching, take into account the uncertainty of future demand and require confidence intervals as the input. However, existing methods for confidence interval modeling rely on strict assumptions, such as unchanging traffic patterns and correct […]

Ver mais

Preliminaries Gaussian distribution log-likelihood Calculus partial derivative Lagrange multiplier EM Algorithm for Gaussian Mixture1 Analysis Maximizing likelihood could not be used in the Gaussian mixture model directly, because of its severe defects which we have come across at ‘Maximum Likelihood of Gaussian Mixtures’. With the inspiration of K-means, a two-step algorithm was developed. The objective function is the log-likelihood function: [ begin{aligned} ln Pr(mathbf{x}|mathbf{pi},mathbf{mu},Sigma)&=ln (Pi_{n=1}^Nsum_{j=1}^{K}pi_kmathcal{N}(mathbf{x}|mathbf{mu}_k,Sigma_k))\ &=sum_{n=1}^{N}ln sum_{j=1}^{K}pi_jmathcal{N}(mathbf{x}_n|mathbf{mu}_j,Sigma_j)\ end{aligned}tag{1} ]

Ver mais

arXiv:2602.05259v1 Announce Type: cross Abstract: The population $mathrm{KL}_{inf}$ is a fundamental quantity that appears in lower bounds for (asymptotically) optimal regret of pure-exploration stochastic bandit algorithms, and optimal stopping time of sequential tests. Motivated by this, an empirical $mathrm{KL}_{inf}$ statistic is frequently used in the design of (asymptotically) optimal bandit algorithms and sequential tests. While nonasymptotic concentration bounds for the empirical $mathrm{KL}_{inf}$ have been developed, their optimality in terms of constants and rates is questionable, and their generality […]

Ver mais

arXiv:2602.00982v1 Announce Type: new Abstract: Visual robustness and neural alignment remain critical challenges in developing artificial agents that can match biological vision systems. We present the winning approaches from Team HCMUS_TheFangs for both tracks of the NeurIPS 2025 Mouse vs. AI: Robust Visual Foraging Competition. For Track 1 (Visual Robustness), we demonstrate that architectural simplicity combined with targeted components yields superior generalization, achieving 95.4% final score with a lightweight two-layer CNN enhanced by Gated Linear Units and observation […]

Ver mais

arXiv:2601.15301v1 Announce Type: new Abstract: The rapid adoption of LLMs has increased the need for reliable AI text detection, yet existing detectors often fail outside controlled benchmarks. We systematically evaluate 2 dominant paradigms (training-free and supervised) and show that both are brittle under distribution shift, unseen generators, and simple stylistic perturbations. To address these limitations, we propose a supervised contrastive learning (SCL) framework that learns discriminative style embeddings. Experiments show that while supervised detectors excel in-domain, they degrade […]

Ver mais