A Perturbation Approach
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
A Perturbation Approach to Unconstrained Linear Bandits
arXiv:2603.28201v2 Announce Type: replace Abstract: We revisit the standard perturbation-based approach of Abernethy et al. in the context of unconstrained Bandit Linear Optimization (uBLO). We show the surprising result that in the unconstrained setting, this approach effectively reduces Bandit Linear Optimization (BLO) to a standard Online Linear Optimization (OLO) problem.
A Self-Consistent Model of Kinetic Alfven Solitons in Pulsar Wind Plasma: Linking Soliton Characteristics to Pulsar Observables
arXiv:2510.25972v2 Announce Type: replace Abstract: A self-consistent model is presented for the formation and propagation of kinetic Alfv\'en (KA) solitons in mass-loaded filaments within the pulsar wind, where a magnetized electron--positron--ion plasma flows along open magnetic field lines beyond the light cylinder. Using a reductive perturbation approach, we derive a Korteweg--de Vries (KdV) equation governing the nonlinear evolution of KA solitons in this environment. The soliton...
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
arXiv:2507.06419v3 Announce Type: replace Abstract: Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human preferences and the limited coverage of available datasets, reward models often fail under distributional shifts or adversarial perturbations. Existing approaches for identifying such failure modes typically...
Layerwise Terminal Discrepancy in Chen's Reverse-Heat Coupling on the Boolean Cube
arXiv:2606.04573v1 Announce Type: cross Abstract: We isolate a layerwise refinement of the terminal testing-discrepancy step in Chen's perturbed reverse-heat approach~\cite{Chen2026} to Talagrand's convolution conjecture on the Boolean cube. Built on the joint-filtration martingale formulation of Chen's coupling, and on Chen's approximate monotonicity and conditional squared-score estimates being available in the joint-filtration form stated below, we prove the localized testing estimate \[...
Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models
Announce Type: replace Abstract: Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is computationally expensive, motivating test-time defenses. Recent approaches exploit how CLIP's visual representations respond to stochastic perturbations: aggregating predictions across noisy views, constructing Gaussian noise-averaged anchors and interpolating features toward...
Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design
arXiv:2606.09266v1 Announce Type : new Abstract: Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that matches the desired response at one frequency may deviate at others, and modifying geometry to improve one sub-band often perturbs neighboring sub-bands. Yet existing broadband inverse-design approaches are either constrained by predefined templates, or rely on image representations that fail to...
C-LEAD: Contrastive Learning for Enhanced Adversarial Defense
arXiv:2510.27249v2 Announce Type: replace Abstract: Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect predictions with small perturbations in input images. Addressing this issue is crucial for deploying robust deep-learning systems.
A Unified Framework for Scalable and Robust Paper Assignment
arXiv:2601.14402v2 Announce Type: replace Abstract: Assigning papers to reviewers is a central challenge in the peer-review process of large academic conferences. Program chairs must balance competing objectives, including maximizing reviewer expertise, promoting diversity, and enhancing robustness to strategic manipulation, but it is challenging to do so at the modern conference scale. Existing algorithmic paper assignment approaches either fail to address all of these goals simultaneously...
Enhancing Hallucination Detection through Noise Injection
arXiv:2502.03799v4 Announce Type: replace Abstract: Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked hallucinations to model uncertainty, suggesting that hallucinations can be detected by measuring dispersion over answer distributions obtained from multiple samples drawn from a model.
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
Announce Type: replace Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced continuous diffusion in image-like generation, we show that it can be an effective first-stage prior for sparse voxel scaffolds. By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete...