SHARP
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Sharp Low-Degree Thresholds for Planted-vs-Planted Testing
arXiv:2606.05266v1 Announce Type: new Abstract: We establish the first sharp thresholds for low-degree polynomial tests in planted-vs-planted settings, where the goal is to determine with vanishing error which of two structured planted mechanisms generated the observed data. We prove matching low-degree upper and lower bounds for counting communities in the planted submatrix and planted dense subgraph models. The resulting testing threshold coincides, down to the sharp constant, with the...
UniSHARP: Universal Sharp Monocular View Synthesis
Announce Type: new Abstract: In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit...
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
arXiv:2606.01827v1 Announce Type: cross Abstract: Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and its variants, like most training algorithms, are sensitive to the choice of learning rate, which is typically selected through extensive...
Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
arXiv:2505.21423v3 Announce Type: replace Abstract: The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness in the Edge-of-Stability regime. In this work, we argue that a comprehensive understanding of the generalization performance of gradient descent requires analyzing the interaction between these various forms of implicit regularization. We empirically demonstrate...
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
arXiv:2606.06855v1 Announce Type: cross Abstract: While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or sub-Gaussian/sub-Weibull tail assumptions, which can be overly restrictive for modern settings with heavy-tailed or unbounded losses. We develop a stability-based framework that requires only a finite $L_p$ moment condition. Our first contribution is sharp...
Markets shake, money slows: Equity mutual funds see sharp dip in inflows
Equity mutual funds saw a sharp slowdown in inflows in May, falling to their lowest level in a year as geopolitical tensions in West Asia, rising crude oil prices and market volatility weighed on investor sentiment, according to data released by the Association of Mutual Funds in India (AMFI). Net inflows into equity schemes stood at Rs 22,908 crore in May, down 40% from Rs 38,440 crore in April. This was also the weakest monthly inflow since May 2025, when the segment had attracted Rs...
Stability Analysis of Sharpness-Aware Minimization
arXiv:2301.06308v2 Announce Type: replace Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains. Instead of minimizing the loss of the current weights, SAM minimizes the worst-case loss in its neighborhood in the parameter space. In this paper, we investigate the convergence instability of SAM near a saddle point.
Sharp rise in demand at food banks since start of Iran war, charities say
Sharp rise in demand at food banks since start of Iran war, charities say Soaring demand coupled with lower donations is creating a ‘perfect storm’ for food banks, leading charity Felix said - Bookmark - CommentsGo to comments Demand for food banks has shot up dramatically since the beginning of the war in Iran, with charities struggling to cope, a leading charity has warned. Providers are reporting soaring costs and fall in donations since the US and Israel launched strikes in February, in...
Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
arXiv:2604.09412v2 Announce Type: replace-cross Abstract: We study the population loss landscape of two-layer ReLU networks of the form $\sum_{k=1}^K \mathrm{ReLU}(w_k^\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact low-dimensional representation in terms of summary statistics, yielding a sharp and interpretable characterisation of the landscape. We further establish a direct link with one-pass SGD: local minima correspond...
Hormuz crisis side effect: a sharp rise in container shipping rates
Hormuz crisis side effect: a sharp rise in container shipping rates - SCFI global composite index has doubled since the war with Iran began and is at its highest point since September 2024, during the Red Sea crisis - Bunker fuel costs have jumped by almost 70% and container lines are successfully passing incremental costs along to shippers - Shanghai-Los Angeles spot rates are up 59% vs late February, with Shanghai-New York rates up 66%, according to Drewry assessments Spot container...