7 papers
Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks
Yuto Omae, Kazuki Sakai, Yohei Kakimoto +3
The flatness hypothesis suggests that flatness of the loss landscape, as measured by the eigenvalues of the loss Hessian, correlates with better neural network generalization. Whil…
Wavelet-Based Extraction of Transient Noise in Gravitational-Wave Interferometers using a Saliency-Guided Learning Architecture
Christopher Allene, Dhruv Kumar, Yusuke Sakai +2
Gravitational-wave interferometers exhibit a wide variety of short-duration non-Gaussian transients, commonly referred to as glitches, that complicate the detection of astrophysica…
Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks
Yuto Omae, Kazuki Sakai, Yohei Kakimoto +3
Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship between loss geometry and generali…
Glitch noise classification in KAGRA O3GK observing data using unsupervised machine learning
Shoichi Oshino, Yusuke Sakai, Marco Meyer-Conde +5
Gravitational wave interferometers are disrupted by various types of nonstationary noise, referred to as glitch noise, that affect data analysis and interferometer sensitivity. The…
Regression of Suspension Violin Modes in KAGRA O3GK Data with Kalman Filters
Lucas Moisset, Marco Meyer-Conde, Christopher Allene +4
Suspension thermal modes in interferometric gravitational-wave detectors produce narrow, high-Q spectral lines that can contaminate gravitational searches and bias parameter estima…
Gravitational Wave Memory from Accelerating Relativistic Jets in Multiple Thick Shell Scenarios
Yusuke Sakai, Ryo Yamazaki, Yoshihiro Okutani +4
Gravitational wave (GW) memory, a permanent distortion of the space-time metric, is anticipated during the acceleration of relativistic jets in gamma-ray bursts (GRBs). While the p…