Copertina

TPV: Parameter Perturbations Through the Lens of Test Prediction Variance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Arpit, Devansh
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

New User Event Prediction Through the Lens of Causal Inference
di: Yuchi, Henry Shaowu, et al.
Pubblicazione: (2024)

CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
di: Si, Haotian, et al.
Pubblicazione: (2025)

Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
di: Fan, Yewen, et al.
Pubblicazione: (2024)

Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
di: Rubbi, Andrea, et al.
Pubblicazione: (2026)

Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models
di: Garg, Arpit, et al.
Pubblicazione: (2025)

SPRINT: Stochastic Performative Prediction With Variance Reduction
di: Xie, Tian, et al.
Pubblicazione: (2025)

Generative Model Inversion Through the Lens of the Manifold Hypothesis
di: Peng, Xiong, et al.
Pubblicazione: (2025)

Rethinking Deep Alignment Through The Lens Of Incomplete Learning
di: Bach, Thong, et al.
Pubblicazione: (2025)

Dense Associative Memory Through the Lens of Random Features
di: Hoover, Benjamin, et al.
Pubblicazione: (2024)

Improved Localized Machine Unlearning Through the Lens of Memorization
di: Torkzadehmahani, Reihaneh, et al.
Pubblicazione: (2024)

On the Variance of Neural Network Training with respect to Test Sets and Distributions
di: Jordan, Keller
Pubblicazione: (2023)

Invisible Traces: Using Hybrid Fingerprinting to identify underlying LLMs in GenAI Apps
di: Bhardwaj, Devansh, et al.
Pubblicazione: (2025)

Identifiable Latent Polynomial Causal Models Through the Lens of Change
di: Liu, Yuhang, et al.
Pubblicazione: (2023)

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
di: Gravina, Alessio, et al.
Pubblicazione: (2024)

Task Arithmetic Through The Lens Of One-Shot Federated Learning
di: Tao, Zhixu Silvia, et al.
Pubblicazione: (2024)

Targeted Variance Reduction: Robust Bayesian Optimization of Black-Box Simulators with Noise Parameters
di: Miller, John Joshua, et al.
Pubblicazione: (2024)

Time Series Forecasting Through the Lens of Dynamics
di: Brachet, Alexis-Raja, et al.
Pubblicazione: (2025)

Explain Variance of Prediction in Variational Time Series Models for Clinical Deterioration Prediction
di: Liu, Jiacheng, et al.
Pubblicazione: (2024)

Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
di: Cheng, Jiashun, et al.
Pubblicazione: (2025)

Reinforcement Learning for Self-Healing Material Systems
di: Chatterjee, Maitreyi, et al.
Pubblicazione: (2025)

LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
di: Agarwal, Devansh, et al.
Pubblicazione: (2025)

Accelerated Smoothing: A Scalable Approach to Randomized Smoothing
di: Bhardwaj, Devansh, et al.
Pubblicazione: (2024)

Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
di: Kolb, Chris, et al.
Pubblicazione: (2025)

Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations
di: Ben-Yair, Ido, et al.
Pubblicazione: (2021)

Eliciting Latent Predictions from Transformers with the Tuned Lens
di: Belrose, Nora, et al.
Pubblicazione: (2023)

Dimension Agnostic Testing of Survey Data Credibility through the Lens of Regression
di: Basu, Debabrota, et al.
Pubblicazione: (2025)

GPT-2 Through the Lens of Vector Symbolic Architectures
di: Knittel, Johannes, et al.
Pubblicazione: (2024)

Weak-to-Strong Generalization Through the Data-Centric Lens
di: Shin, Changho, et al.
Pubblicazione: (2024)

Causal Layering via Conditional Entropy
di: Feigenbaum, Itai, et al.
Pubblicazione: (2024)

When Can We Track Significant Preference Shifts in Dueling Bandits?
di: Suk, Joe, et al.
Pubblicazione: (2023)

Non-Stationary Dueling Bandits Under a Weighted Borda Criterion
di: Suk, Joe, et al.
Pubblicazione: (2024)

Parameter Efficient Fine-tuning via Explained Variance Adaptation
di: Paischer, Fabian, et al.
Pubblicazione: (2024)

Ensemble Performance Through the Lens of Linear Independence of Classifier Votes in Data Streams
di: Bektas, Enes, et al.
Pubblicazione: (2025)

Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens
di: Nikolaou, Konstantin, et al.
Pubblicazione: (2025)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
di: Honarpisheh, Arya, et al.
Pubblicazione: (2025)

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
di: Gong, Zhuocheng, et al.
Pubblicazione: (2024)

PoPE: Legendre Orthogonal Polynomials Based Position Encoding for Large Language Models
di: Aggarwal, Arpit
Pubblicazione: (2024)

Editing Arbitrary Propositions in LLMs without Subject Labels
di: Feigenbaum, Itai, et al.
Pubblicazione: (2024)

Optimization of the Model Predictive Control Meta-Parameters Through Reinforcement Learning
di: Bøhn, Eivind, et al.
Pubblicazione: (2021)

Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
di: Tokarchuk, Evgeniia, et al.
Pubblicazione: (2026)