Exploring Bad Minima in Transfer Learning
cs.LG, cs.CR
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/facebookresearch/vissl
Terminology
Sources
- Exploring the Limits of Large Scale Pre-training
- Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications
- Poisoning Attacks against Support Vector Machines
- Deep Clustering for Unsupervised Learning of Visual Features
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- A Simple Framework for Contrastive Learning of Visual Representations
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Unsupervised Visual Representation Learning by Context Prediction
- Unsupervised Representation Learning by Predicting Image Rotations
- Deep Residual Learning for Image Recognition
- Momentum Contrast for Unsupervised Visual Representation Learning
- Understanding Generalization through Visualizations
- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
- Bad Global Minima Exist and SGD Can Reach Them
- Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
- Efficient Estimation of Word Representations in Vector Space
- Self-Supervised Learning of Pretext-Invariant Representations
- Poisoning Attacks with Generative Adversarial Nets
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning