Cover Image

Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Lin, Qingwei
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decoupled Split Learning via Auxiliary Loss
by: Zihad, Anower, et al.
Published: (2026)

Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
by: Premi, Santosh
Published: (2026)

An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
by: Zhang, Qizhen, et al.
Published: (2026)

Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets
by: Malek, Idriss, et al.
Published: (2025)

A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization
by: Manir, Shalima Binta, et al.
Published: (2026)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
by: Lv, Ang, et al.
Published: (2025)

Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
by: Wang, Lean, et al.
Published: (2024)

Revisiting Generalization Measures Beyond IID: An Empirical Study under Distributional Shift
by: Nakai, Sora, et al.
Published: (2026)

Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction
by: Dam, Harvey, et al.
Published: (2025)

Revisiting Experience Replayable Conditions
by: Kobayashi, Taisuke
Published: (2024)

Improving GBDT Performance on Imbalanced Datasets: An Empirical Study of Class-Balanced Loss Functions
by: Luo, Jiaqi, et al.
Published: (2024)

Estimation of the Learning Coefficient Using Empirical Loss
by: Takio, Tatsuyoshi, et al.
Published: (2025)

Differentiable Energy-Based Regularization in GANs: A Simulator-Based Exploration of VQE-Inspired Auxiliary Losses
by: Strnadel, David
Published: (2025)

Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency
by: Dwyer, Joe
Published: (2026)

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective
by: Wang, Zexin, et al.
Published: (2024)

Consistency Conditions for Differentiable Surrogate Losses
by: Khurana, Drona, et al.
Published: (2025)

VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
by: Ray, Rahul D, et al.
Published: (2026)

Consistent Optimal Transport with Empirical Conditional Measures
by: Manupriya, Piyushi, et al.
Published: (2023)

Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions
by: Ma, Tianhao, et al.
Published: (2024)

Empirically Calibrated Conditional Independence Tests
by: Pan, Milleno, et al.
Published: (2026)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
by: Bai, Zhiwei, et al.
Published: (2022)

Adaptive Computation Depth via Learned Token Routing in Transformers
by: Mohammed, Ahmed Abdelmuniem Abdalla
Published: (2026)

Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness
by: Shin, Baekrok, et al.
Published: (2026)

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
by: Fang, Kun, et al.
Published: (2023)

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing
by: Filippova, Anastasiia, et al.
Published: (2026)

Spectral Condition for $μ$P under Width-Depth Scaling
by: Zheng, Chenyu, et al.
Published: (2026)

Doing well with less! On Sampling Techniques for Empirical Pairwise Loss Estimation/Minimization
by: Davy, Louise, et al.
Published: (2026)

An Empirical Study of Aegis
by: Saragih, Daniel, et al.
Published: (2024)

Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions
by: Lee, Youngjoon, et al.
Published: (2025)

HI-GAN: Hierarchical Inpainting GAN with Auxiliary Inputs for Combined RGB and Depth Inpainting
by: Dash, Ankan, et al.
Published: (2024)

Generating Auxiliary Tasks with Reinforcement Learning
by: Goldfeder, Judah, et al.
Published: (2025)

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
by: Yang, Yongjin, et al.
Published: (2025)

MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale
by: Falke, Tobias, et al.
Published: (2026)

On Evaluating Loss Functions for Stock Ranking: An Empirical Analysis With Transformer Model
by: Kwiatkowski, Jan, et al.
Published: (2025)

Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
by: Merrill, William, et al.
Published: (2025)

LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing
by: Li, Yang
Published: (2025)

SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes
by: Nunepalli, Bharath
Published: (2025)

More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing
by: Shaier, Sagi, et al.
Published: (2024)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
by: Fu, Yuqian, et al.
Published: (2026)

An Empirical Study of Qwen3 Quantization
by: Zheng, Xingyu, et al.
Published: (2025)