"loss landscape analysis" Papers
18 papers found
Conference
Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses
Han Bao, Shinsaku Sakaue, Yuki Takezawa
NEURIPS 2025spotlightarXiv:2502.04889
1
citations
Attention with Markov: A Curious Case of Single-layer Transformers
Ashok Makkuva, Marco Bondaschi, Adway Girish et al.
ICLR 2025arXiv:2402.04161
39
citations
Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities
Chengkun Sun, Jinqian Pan, Zhuoli Jin et al.
AAAI 2025paperarXiv:2409.13154
1
citations
How Far Are We from True Unlearnability?
Kai Ye, Liangcai Su, Chenxiong Qian
ICLR 2025arXiv:2509.08058
4
citations
Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
Akira Ito, Masanori Yamada, Atsutoshi Kumagai
ICML 2025
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
Frank Zhengqing Wu, Berfin Simsek, François Ged
ICLR 2025arXiv:2402.05626
2
citations
Revisiting Mode Connectivity in Neural Networks with Bezier Surface
Jie Ren, Pin-Yu Chen, Ren Wang
ICLR 2025
3
citations
RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
Yingsha Xie, Rui Min, Zeyu Qin et al.
NEURIPS 2025
Theoretical Insights into In-context Learning with Unlabeled Data
Yingcong Li, Xiangyu Chang, Muti Kara et al.
NEURIPS 2025
Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
Minhak Song, Beomhan Baek, Kwangjun Ahn et al.
NEURIPS 2025arXiv:2507.09846
2
citations
Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes
Jumin Han, Jun-Hui Kim, Seong-Whan Lee
NEURIPS 2025
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao et al.
ICLR 2025arXiv:2404.14309
7
citations
Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
Xuyang Zhong, Yixiao Huang, Chen Liu
NEURIPS 2025
Challenges in Training PINNs: A Loss Landscape Perspective
Pratik Rathore, Weimu Lei, Zachary Frangella et al.
ICML 2024arXiv:2402.01868
116
citations
Flatness-aware Sequential Learning Generates Resilient Backdoors
Hoang Pham, The-Anh Ta, Anh Tran et al.
ECCV 2024arXiv:2407.14738
1
citations
Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
Yixiong Zou, Yicong Liu, Yiman Hu et al.
CVPR 2024arXiv:2403.00567
23
citations
MD tree: a model-diagnostic tree grown on loss landscape
Yefan Zhou, Jianlong Chen, Qinxue Cao et al.
ICML 2024arXiv:2406.16988
2
citations
Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning
Jing Xu, Jingzhao Zhang
ICML 2024arXiv:2405.02596
13
citations