arXiv research

System predicts ice formation to improve road safety.

LLM forecasting benchmarks suffer from information leakage, which confounds model performance.

Probabilistic programming aids in automatically dating ice cores, reducing manual error and uncertainty.

Generative AI predicts Arctic sea ice dynamics over decades.

The paper defines and analyzes IC using high-dimensional directional statistics.

New neural network enforces mass conservation for better ice flow predictions.

The study analyzes the differences between physical and risk-neutral correlation estimates for equity baskets.

The electroencephalogram (EEG) provides a non-invasive, minimally restrictive, and relatively low cost measure of mesoscale brain dynamics with high temporal resolution. Although signals recorded in parallel by multiple, near-adjacent EEG scalp electrode channels are highly-correlated and combine signals from many diff…

IC-Network improves CNNs by integrating elastic collision units.

Investigates the use of Information Coefficient as a stock selection model performance measure.

Proposes ICE-based metric for better understanding interactions in black-box models.

ICE proposes a new loss function for deep metric learning.

Adversarial attacks hide cyber-physical attacks in ICS.

This paper analyzes and improves the effectiveness of BN techniques in controlling Internal Covariate Shift.

New method corrects seasonal Arctic sea ice predictions with probabilistic models.

Neural-network emulators predict sea-level changes due to Antarctic ice melt.

New DR-IC estimator reduces bias and variance in OPE.

We propose a novel iterative channel estimation (ICE) algorithm that essentially removes the critical known noisy channel assumption for universal discrete denoising problem. Our algorithm is based on Neural DUDE (N-DUDE), a recently proposed neural network-based discrete denoiser, and it estimates the channel transiti…

Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future video frame predict…

Introduces injective category number for continuous maps, linking classical and contemporary research.

A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical eviden…

This paper identifies and bounds ICE central moments using PO marginal central moments.

ICE-Pruning accelerates deep neural network pruning by 9.61x.

We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.

Wind power, as an alternative to burning fossil fuels, is abundant and inexhaustible. To fully utilize wind power, wind farms are usually located in areas of high altitude and facing serious ice conditions, which can lead to serious consequences. Quick detection of blade ice accretion is crucial for the maintenance of …

In this paper we consider two semimartingales driven by diffusions and jumps. We allow both for finite activity and for infinite activity jump components. Given discrete observations we disentangle the {\it integrated covariation} (the covariation between the two diffusion parts, indicated by IC) from the co-jumps. Thi…

New method for online learning IC models with node-level feedback.

In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact that independent components must be whitened, we introduce a novel Independent-…

We present a procedure which allows one to integrate explicitly the class of checkerboard IC-nets which has recently been introduced as a generalisation of incircular (IC) nets. The latter class of privileged congruences of lines in the plane is known to admit a great variety of geometric properties which are also pres…

Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm works the best on a particular problem. We believe that the two crucial steps of MC…

New method prevents posterior collapse in iVAE models.

Modeling vessel speed to balance efficiency and environmental risks in Arctic shipping.

This paper detects torsion elements in homology cylinder monoids.

A new IC-Connection improves disentanglement in conditional GANs.

We consider congruences of straight lines in a plane with the combinatorics of the square grid, with all elementary quadrilaterals possessing an incircle. It is shown that all the vertices of such nets (we call them incircular or IC-nets) lie on confocal conics. Our main new results are on checkerboard IC-nets in the p…

Paper tackles imbalanced binary classification by optimizing precision and recall directly.

Paper introduces IC-index to evaluate interaction prediction methods.

A new stock selection strategy uses combined machine learning with dynamic weighting methods.

We test three common information criteria (IC) for selecting the order of a Hawkes process with an intensity kernel that can be expressed as a mixture of exponential terms. These processes find application in high-frequency financial data modelling. The information criteria are Akaike's information criterion (AIC), the…

Discusses handling intercurrent events in clinical trials with time-to-event outcomes.

Canonical parametrisations of classical confocal coordinate systems are introduced and exploited to construct non-planar analogues of incircular (IC) nets on individual quadrics and systems of confocal quadrics. Intimate connections with classical deformations of quadrics which are isometric along asymptotic lines and …

Due to the increasing complexity of Integrated Circuits (ICs) and System-on-Chip (SoC), developing high-quality synthesis flows within a short market time becomes more challenging. We propose a general approach that precisely estimates the Quality-of-Result (QoR), such as delay and area, of unseen synthesis flows for s…

We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural networks to approximate a posterior distribution over latent variables in a probabi…

Study characterizes cryospheric spectral feature space using joint PC+t-SNE approach.

Study polynomial trace identities in $SL(2,\IC)$ using quaternion algebras.

Antifreeze proteins (AFPs) are the sub-set of ice binding proteins indispensable for the species living in extreme cold weather. These proteins bind to the ice crystals, hindering their growth into large ice lattice that could cause physical damage. There are variety of AFPs found in numerous organisms and due to the h…

Let R be a compact oriented surface of genus g with one boundary component. Homology cylinders over R form a monoid IC into which the Torelli group I of R embeds by the mapping cylinder construction. Two homology cylinders M and M' are said to be Y_k-equivalent if M' is obtained from M by "twisting" an arbitrary surfac…

New method enhances hotspot prediction in IC designs.