No article text was recorded for this version.
surrogate loss misalignment
Version 1 of 1132 papers139 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Consistent Lebesgue Measure for Multi-label Learning
- Blog: Yordle: An Efficient Imitation Learning for Branch and Bound
- Blog: Ranking Measures and Loss Functions in Learning to Rank
- Blog: Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
- Blog: A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance
- Blog: Structured learning for non-smooth ranking losses
- Blog: Simpson's Bias in NLP Training
- Blog: Fast Data Mixture Optimization via Gradient Descent
- Blog: Scalable Learning of Non-Decomposable Objectives
- Blog: Automated Essay Scoring by Maximizing Human-Machine Agreement
- Blog: End-to-end training of object class detectors for mean average precision
- Blog: Listwise Learning to Rank Based on Approximate Rank Indicators
- Blog: Towards Accurate One-Stage Object Detection with AP-Loss
- Blog: Building Accurate Simple Models with Multihop
- Blog: Relational Surrogate Loss Learning
- Blog: Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders
- Blog: DeepMOT: A Differentiable Framework for Training Multiple Object Trackers
- Blog: Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers
- Blog: Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
- Blog: Risk Minimization in Structured Prediction using Orbit Loss
- Blog: Recall@k Surrogate Loss with Large Batches and Similarity Mixup
- Blog: AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
- Blog: Coin_flipper at eHealth-KD Challenge 2019: Voting LSTMs for Key Phrases and Semantic Relation Identification Applied to Spanish eHealth Texts
- Blog: Training Over-parameterized Models with Non-decomposable Objectives
- Blog: Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice
- Blog: Training Speaker Enrollment Models by Network Optimization
- Blog: Learnable Structured Clustering Framework for Deep Metric Learning
- Blog: Improving Model Classification by Optimizing the Training Dataset
- Blog: Optimizing Black-box Metrics with Iterative Example Weighting
- Blog: Relational Surrogate Loss Learning
- Blog: Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences
- Blog: A Unified Framework of Surrogate Loss by Refactoring and Interpolation
- Blog: Loss Functions for Top-k Error: Analysis and Insights
- Blog: GLA-Net: An Attention Network with Guided Loss for Mismatch Removal
- Blog: Optimizing Evaluation Metrics for Multi-Task Learning via the Alternating Direction Method of Multipliers
- Blog: Finding Pareto trade-offs in fair and accurate detection of toxic speech
- Blog: Optimizing Multivariate Performance Measures from Multi-View Data
- Blog: Optimizing estimated loss reduction for active sampling in rank learning
- Blog: AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
- Blog: Recall@k Surrogate Loss with Large Batches and Similarity Mixup
- Blog: Deep Hashing Network for Efficient Similarity Retrieval
- Blog: Learning Surrogate Losses
- Blog: Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance
- Blog: Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching
- Blog: Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
- Blog: Optimization of False Acceptance/Rejection Rates and Decision Threshold for End-to-End Text-Dependent Speaker Verification Systems
- Blog: ALBA: Reinforcement Learning for Video Object Segmentation
- Blog: Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
- Blog: Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors
- Blog: Editorial Introduction to the Special Issue on Biometrics at a Distance in the Deep Learning Era
- Blog: Joint Calibration for Semantic Segmentation
- Blog: Discriminative Metric Learning by Neighborhood Gerrymandering
- Blog: ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation
- Blog: Escaping the curse of dimensionality in similarity learning: Efficient Frank-Wolfe algorithm and generalization bounds
- Blog: MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
- Blog: sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification
- Blog: One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
- Blog: Learning Surrogates via Deep Embedding
- Blog: Direct Maximization of Average Precision by Hill-Climbing, with a Comparison to a Maximum Entropy Approach
- Blog: Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
Showing 60 of 132 papers.
History & citation
Current · Permanent link
- This direction split from Aligning Surrogate Losses with Task Evaluation Metrics (78% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_surrogate_loss_misalignment_04dd99f9,
title = {surrogate loss misalignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/surrogate-loss-misalignment/rdr_04dd99f91c454074b61b443985832a51},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_surrogate_loss_misalignment_04dd99f9_v1,
title = {surrogate loss misalignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/surrogate-loss-misalignment/rdr_04dd99f91c454074b61b443985832a51/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}