paper-with-me

Papers

Can gradient clipping mitigate label noise?

2020-05-01 · ICLR 2020 1 · Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

Gradient clipping is a widely-used technique in the training of deep networks, and is generally motivated from an optimisation lens: informally, it controls the dynamics of iterates, thus enhancing the rate of convergence to a local minimum. This intuition has been made precise in a line of recent works, which show that suitable clipping can yield significantly faster convergence than vanilla gradient descent. In this paper, we propose a new lens for studying gradient clipping, namely, robustness: informally, one expects clipping to provide robustness to noise, since one does not overly trust any single sample. Surprisingly, we prove that for the common problem of label noise in classification, standard gradient clipping does not in general provide robustness. On the other hand, we show that a simple variant of gradient clipping is provably robust, and corresponds to suitably modifying the underlying loss function. This yields a simple, noise-robust alternative to the standard cross-entropy loss which performs well empirically.

📄 PDF Abstract BibTeX

Code (1)

dmizr/phuber pytorch

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Similar Papers 제목 키워드 기반

Optimized Gradient Clipping for Noisy Label Learning

2024-12-12 · Xichen Ye, Yifan Wu, Weizhong Zhang, Xiaoqiang Li 외

Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed opt…

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches

2024-10-08 · Meifan Zhang, Zhanhong Xie, Lihua Yin

Federated learning (FL) faces two primary challenges: the risk of privacy leakage due to parameter sharing and communication inefficiencies. To address these challenges, we propose DPSFL, a federated learning method that…

Federated Learning

Enhancing LLM Training via Spectral Clipping

2026-03-15 · Xiaowen Jiang, Andrei Semenov, Sebastian U. Stich arxiv

While spectral-based optimizers like Muon operate directly on the spectrum of updates, standard adaptive methods such as AdamW do not account for the spectral structure of weights and gradients, leaving them vulnerable t…

Technical Report: Full Version of Analyzing and Optimizing Perturbation of DP-SGD Geometrically

2025-04-08 · Jiawei Duan, Haibo Hu, Qingqing Ye, Xinyue Sun

Differential privacy (DP) has become a prevalent privacy model in a wide range of machine learning tasks, especially after the debut of DP-SGD. However, DP-SGD, which directly perturbs gradients in the training iteration…

Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering

2025-11-11 · Xincheng Xu, Thilina Ranbaduge, Qing Wang, Thierry Rakotoarivelo 외 arxiv

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by …