Image de couverture de livre

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Attias, Idan, Dziugaite, Gintare Karolina, Haghifam, Mahdi, Livni, Roi, Roy, Daniel M.
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On Traceability in $\ell_p$ Stochastic Convex Optimization
par: Voitovych, Sasha, et autres
Publié: (2025)

The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
par: Livni, Roi
Publié: (2024)

All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
par: Burla, Tal, et autres
Publié: (2026)

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
par: Sharma, Ekansh, et autres
Publié: (2024)

Rapid Overfitting of Multi-Pass Stochastic Gradient Descent in Stochastic Convex Optimization
par: Vansover-Hager, Shira, et autres
Publié: (2025)

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
par: Livni, Roi
Publié: (2023)

Improved Localized Machine Unlearning Through the Lens of Memorization
par: Torkzadehmahani, Reihaneh, et autres
Publié: (2024)

Detoxifying LLMs via Representation Erasure-Based Preference Optimization
par: Sepahvand, Nazanin Mohammadi, et autres
Publié: (2026)

A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees
par: Ryabchenko, Alexander, et autres
Publié: (2026)

Simultaneous linear connectivity of neural networks modulo permutation
par: Sharma, Ekansh, et autres
Publié: (2024)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
par: Baluta, Teodora, et autres
Publié: (2024)

Less is More: Undertraining Experts Improves Model Upcycling
par: Horoi, Stefan, et autres
Publié: (2025)

Data Selection for Transfer Unlearning
par: Sepahvand, Nazanin Mohammadi, et autres
Publié: (2024)

Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
par: Liu, Ziyi, et autres
Publié: (2024)

Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
par: Liu, Ziyi, et autres
Publié: (2024)

Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs
par: Ryabchenko, Alexander, et autres
Publié: (2025)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
par: Yang, Yu, et autres
Publié: (2023)

Dataset Difficulty and the Role of Inductive Bias
par: Kwok, Devin, et autres
Publié: (2024)

Leveraging Function Space Aggregation for Federated Learning at Scale
par: Dhawan, Nikita, et autres
Publié: (2023)

The Sample Complexity of Membership Inference and Privacy Auditing
par: Haghifam, Mahdi, et autres
Publié: (2025)

Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning
par: Attias, Idan, et autres
Publié: (2026)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
par: Guo, Phillip, et autres
Publié: (2024)

Soup to go: mitigating forgetting during continual learning with model averaging
par: Kleiman, Anat, et autres
Publié: (2025)

Adversarially Robust PAC Learnability of Real-Valued Functions
par: Attias, Idan, et autres
Publié: (2022)

We Should Separate Memorization from Copyright
par: Haviv, Adi, et autres
Publié: (2026)

Evaluating Interventional Reasoning Capabilities of Large Language Models
par: Kasetty, Tejas, et autres
Publié: (2024)

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
par: Dughmi, Shaddin, et autres
Publié: (2026)

Leveraging Per-Instance Privacy for Machine Unlearning
par: Sepahvand, Nazanin Mohammadi, et autres
Publié: (2025)

Low Resource Reconstruction Attacks Through Benign Prompts
par: Yarkoni, Sol, et autres
Publié: (2025)

Private Geometric Median
par: Haghifam, Mahdi, et autres
Publié: (2024)

Sample Compression Scheme Reductions
par: Attias, Idan, et autres
Publié: (2024)

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability
par: Attias, Idan, et autres
Publié: (2022)

Stochastic Difference-of-Convex Optimization with Momentum
par: Chayti, El Mahdi, et autres
Publié: (2025)

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
par: Ohib, Riyasat, et autres
Publié: (2024)

Credit Attribution and Stable Compression
par: Livni, Roi, et autres
Publié: (2024)

Torque-Aware Momentum
par: Malviya, Pranshu, et autres
Publié: (2024)

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
par: Jin, Tian, et autres
Publié: (2025)

Continual Learning in Vision-Language Models via Aligned Model Merging
par: Sokar, Ghada, et autres
Publié: (2025)

Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning
par: Attias, Idan, et autres
Publié: (2025)

Can Copyright be Reduced to Privacy?
par: Elkin-Koren, Niva, et autres
Publié: (2023)