Cover Image

Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Das, Abhijit, Dutta, Sayantan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting
by: Xiao, Yang, et al.
Published: (2025)

Pruning-aware Loss Functions for STOI-Optimized Pruned Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay
by: Hinrichs, Reemt, et al.
Published: (2025)

Speech Foundation Models Generalize to Time Series Tasks from Wearable Sensor Data
by: Narain, Jaya, et al.
Published: (2025)

Text-Independent Speaker Identification Using Audio Looping With Margin Based Loss Functions
by: Garcia, Elliot Q C, et al.
Published: (2025)

Multi-Source Music Generation with Latent Diffusion
by: Xu, Zhongweiyang, et al.
Published: (2024)

VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space
by: Rodriguez, Armani, et al.
Published: (2024)

Zero Shot Audio to Audio Emotion Transfer With Speaker Disentanglement
by: Dutta, Soumya, et al.
Published: (2024)

Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias
by: Seo, Joonwon
Published: (2026)

On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation
by: Pettenó, Matteo, et al.
Published: (2025)

GE2E-AC: Generalized End-to-End Loss Training for Accent Classification
by: Watanabe, Chihiro, et al.
Published: (2024)

Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
by: Hayta, Berk, et al.
Published: (2026)

Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?
by: Feng, Tiantian, et al.
Published: (2024)

Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning
by: Franzreb, Carlos, et al.
Published: (2025)

On the Condition Monitoring of Bolted Joints through Acoustic Emission and Deep Transfer Learning: Generalization, Ordinal Loss and Super-Convergence
by: Ramasso, Emmanuel, et al.
Published: (2024)

Voice Disorder Analysis: a Transformer-based Approach
by: Koudounas, Alkis, et al.
Published: (2024)

Unsupervised Speaker Diarization in Distributed IoT Networks Using Federated Learning
by: Bhuyan, Amit Kumar, et al.
Published: (2024)

RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responses
by: Xu, Shaoheng, et al.
Published: (2026)

Arabic ASR on the SADA Large-Scale Arabic Speech Corpus with Transformer-Based Models
by: Gerazov, Branislav, et al.
Published: (2025)

ResidualTransformer: Residual Low-Rank Learning with Weight-Sharing for Transformer Layers
by: Wang, Yiming, et al.
Published: (2023)

Do Foundational Audio Encoders Understand Music Structure?
by: Toyama, Keisuke, et al.
Published: (2025)

Parameter-Efficient Transfer Learning for Music Foundation Models
by: Ding, Yiwei, et al.
Published: (2024)

BiFormer3D: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer
by: Xu, Shaoheng, et al.
Published: (2026)

Safeguarding Privacy in Edge Speech Understanding with Tiny Foundation Models
by: Benazir, Afsara, et al.
Published: (2025)

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis
by: Sarkar, Eklavya, et al.
Published: (2024)

Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings
by: Wisnu, Dyah A. M. G., et al.
Published: (2025)

Foundation Model Hidden Representations for Heart Rate Estimation from Auscultation
by: Nie, Jingping, et al.
Published: (2025)

Predictive-Generative Drift Decomposition for Speech Enhancement and Separation
by: Richter, Julius, et al.
Published: (2026)

Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses
by: Zhao, Shengkui, et al.
Published: (2021)

Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset
by: Cheston, Huw, et al.
Published: (2025)

Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
by: Kienegger, Jakob, et al.
Published: (2024)

Anticipatory Music Transformer
by: Thickstun, John, et al.
Published: (2023)

Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses
by: Jeong, Seung Gyu, et al.
Published: (2025)

Learning to Discover: A Generalized Framework for Raga Identification without Forgetting
by: Singh, Parampreet, et al.
Published: (2026)

PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting
by: Chernyak, Bronya Roni, et al.
Published: (2025)

SpeechOp: Inference-Time Task Composition for Generative Speech Processing
by: Lovelace, Justin, et al.
Published: (2025)

USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models
by: Zhao, Guanlong, et al.
Published: (2023)

Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions
by: Ashvin, Aditya, et al.
Published: (2024)

E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models
by: Dong, Jiaheng, et al.
Published: (2025)

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
by: Fu, Yonggan, et al.
Published: (2022)

Rethinking Speaker Embeddings for Speech Generation: Sub-Center Modeling for Capturing Intra-Speaker Diversity
by: Ulgen, Ismail Rasim, et al.
Published: (2024)