ML model diagnostics: Understanding when and why ML models fail, and determining the appropriate actions to address these failures.

S. Deng, B. Liao, Z. Ouyang, T. Pang, Y. Yang, "Depth, Not Data: An Analysis of Hessian Spectral Bifurcation", (Full Version, Code), 2026.

S. Deng, B. Liao, Z. Ouyang, T. Pang, M. Song, Y. Yang, "Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis", (Full Version, Code), Algorithmic Learning Theory (ALT), 2026.

Z. Liu, O. Balabanov, Y. Yang, M. W. Mahoney, "Learning to Discover Iterative Spectral Algorithms", (Full Version, Code), 2026.

J. Chen, N. Hadler, T. Xie, R. Hnatyshyn, C. Geniesse, Y. Yang, M. W. Mahoney, T. Perciano, J. F. Hartwig, R. Maciejewski, G. H. Weber, "Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis", (Full Version, Code), 2026.

M. Sakarvadia, K. Hegazy, A. Totounferoush, K. Chard, Y. Yang, I. Foster, M. W. Mahoney, "The false promise of zero-shot super-resolution in machine-learned operators", (Full Version, Code), ICLR 2026.

V. Kothapalli, T. Pang, S. Deng, Z. Liu, Y. Yang, "From spikes to heavy tails: Unveiling the spectral evolution of neural networks", (Full Version, Code), Transactions on Machine Learning Research (TMLR), 2025.

K. Schürholt, L. Meynent, Y. Zhou, H. Lu, Y. Yang, D. Borth, "A model zoo on phase transitions in neural networks", (Full Version, Code), Journal of Data-centric Machine Learning Research (DMLR), 2025.

Y. Hu, K. Goel, V. Killiakov, Y. Yang, "Eigenspectrum analysis of neural networks without aspect ratio bias", (Full Version, Code), ICML 2025.

Z. Liu, T. Pang, O. Balabanov, C. Yang, T. Huang, L. Yin, Y. Yang, S. Liu, "LIFT the veil for the truth: principal weights emerge after rank reduction for reasoning-focused supervised fine-tuning", (Full Version, Code), ICML 2025.

L. Hsiung, T. Pang, Y.-C. Tang, L. Song, T.-Y. Ho, P.-Y. Chen, Y. Yang, "Why LLM safety guardrails collapse after fine-tuning: A similarity analysis between alignment and fine-tuning datasets", (Full Version, Blog), ICML Workshop on Data in Generative Models - The Bad, the Ugly, and the Greats, 2025 (Oral).

X. Liu, L. Hsiung, Y. Yang, Y. Yan, "Spectral insights into data-oblivious critical layers in large language models", (Full Version, Code, Blog), ACL 2025 (Findings).

T. Xie, J. Chen, Y. Yang, C. Geniesse, G. Shi, A. Chaudhari, J. K. Cava, M. W. Mahoney, T. Perciano, G. H. Weber, R. Maciejewski, "LossLens: Diagnostics for machine learning through loss landscape visual analytics", (Full Version, Video, Code), IEEE Computer Graphics and Applications, 2025.

M. Sakarvadia, A. Ajith, A. Khan, N. Hudson, C. Geniesse, K. Chard, Y. Yang, I. Foster, M. W. Mahoney, "Mitigating memorization in language models", (Full Version, Code, Blog), ICLR 2025 (Spotlight).

H. Lu*, Y. Zhou*, S. Liu, Z. Wang, M. W. Mahoney, Y. Yang, "AlphaPruning: Using heavy-tailed self regularization theory for improved layer-wise pruning of large language models", (Full Version, Code), NeurIPS 2024.

H. Lu*, X. Liu*, Y. Zhou*, Q. Li*, K. Keutzer, M. W. Mahoney, Y. Yan, H. Yang, Y. Yang, "Sharpness-diversity tradeoff: Improving flat ensembles with SharpBalance", (Full Version, Code), NeurIPS 2024.

C. Geniesse, J. Chen, T. Xie, G. Shi, Y. Yang, D. Morozov, T. Perciano, M. W. Mahoney, R. Maciejewski, G. H. Weber, "Visualizing loss functions as topological landscape profiles", (Full Version), NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2024.

Z. Liu, Y. Hu, T. Pang, Y. Zhou, P. Ren, Y. Yang, "Model balancing helps low-data training and fine-tuning", (Full Version, Code), EMNLP 2024 (Main Conference, Oral).

P Qing, C Gao, Y Zhou, X Diao, Y Yang, S Vosoughi, "AlphaLoRA: Assigning LoRA experts based on layer training quality", (Full Version, Code), EMNLP 2024 (Main Conference).

A. Panda, C. A. Choquette-Choo, Z. Zhang, Y. Yang, P. Mittal, "Teach LLMs to phish: stealing private information from language models", (Full Version), ICLR 2024.

Y. Zhou*, J. Chen*, Q. Cao, K. Schürholt, Y. Yang, "MD tree: a model-diagnostic tree grown on loss landscape", (Full Version, Code, Video), ICML 2024.

Y. Zhou*, T. Pang*, K. Liu, C. H. Martin, M. W. Mahoney, Y. Yang, "Temperature balancing, layer-wise weight analysis, and neural network training", (Full Version, Code), NeurIPS 2023 (Spotlight).

R. Theisen, H. Kim, Y. Yang, L. Hodgkinson, M. W. Mahoney, "When are ensembles really effective?", (Full Version), NeurIPS 2023.

Y. Zhou, Y. Yang, A. Chang, M. W. Mahoney, "A three-regime model of network pruning", (Full Version, code), ICML 2023.

Y. Yang, R. Theisen, L. Hodgkinson, J. E. Gonzalez, K. Ramchandran, C. H. Martin, M. W. Mahoney, "Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data", (Full Version, code), KDD 2023.

Z. Zhang*, A. Panda*, L. Song, Y. Yang, M. W. Mahoney, J. E. Gonzalez, K. Ramchandran, P. Mittal, "Neurotoxin: Durable backdoors in federated learning", (Full Version, code), ICML 2022 (Spotlight).

Y. Yang, L. Hodgkinson, R. Theisen, J. Zou, J. E. Gonzalez, K. Ramchandran, M. W. Mahoney, "Taxonomizing local versus global structure in neural network loss landscapes", (Full Version, video, code), NeurIPS 2021.

Z. Zhang*, Y. Yang*, Z. Yao*, Y. Yan, J. E. Gonzalez, M. W. Mahoney, "Improving semi-supervised federated learning by reducing the gradient diversity of models", (Full Version, code), IEEE BigData 2021.

A. Pham, E. Chan, V. Srivatsa, D. Ghosh, Y. Yang, Y. Yu, R. Zhong, J. E. Gonzalez, J. Steinhardt, "The effect of model size on worst-group generalization", (Full Version) preliminary version accepted by NeurIPS Workshop 2021.

Y. Yang, R. Khanna, Y. Yu, A. Gholami, K. Keutzer, J. E. Gonzalez, K. Ramchandran, M. W. Mahoney, "Boundary thickness and robustness in learning models" (Full Version, code), NeurIPS 2020.

ML on structured data, such as point clouds and graphs.

H. Wang, Y. Mao, Y. Yan, Y. Yang, J. Sun, K. Choi, B. Veeramani, A. Hu, E. Bowen, T. Cody, D. Zhou, EvoluNet: advancing dynamic non-IID transfer learning on graphs, (Full Version, code), ICML 2024.

Y. Yan, M. Hashemi, K. Swersky, Y. Yang, D. Koutra, "Two sides of the same coin: heterophily and oversmoothing in graph convolutional neural networks", (Full Version, code), ICDM 2022.

S. Xiang, A. Yang, Y. Xue, Y. Yang, C. Feng, "Contrastive spatial reasoning on multi-view line drawings", (Full Version, code), CVPR 2022.

P. Trivedi, E. S. Lubana, Y. Yan, Y. Yang, D. Koutra, "Augmentations in graph contrastive learning: Current methodological flaws & towards better practices", (Full Version, code), WWW 2022.

Y. Zhou, Y. Shen, Y. Yan, C. Feng, and Y. Yang, "A dataset-dispersion perspective on reconstruction versus recognition in single-view 3D reconstruction networks", (Full Version, code, video), 3DV 2021.

S. Chen, C. Duan, Y. Yang, D. Li, C. Feng, D. Tian. "Deep unsupervised learning of 3D point clouds via graph topology inference and filtering", (Full Version), IEEE Transactions on Image Processing, vol. 29, no. 12, pp. 3183 - 3198, Dec 2019.

Y. Yang, C. Feng, Y. Shen, D. Tian, "FoldingNet: Point cloud auto-encoder via deep grid deformation" (Full Version, code, video), CVPR 2018 (Spotlight).

Y. Shen, C. Feng, Y. Yang and D. Tian, "Mining point cloud local structures by kernel correlation and graph pooling" (Full Version, code), CVPR 2018.

S. Chen, Y. Yang, S. Zong, A. Singh, J. Kovačević. "Detecting localized categorical attributes on graphs" (Link), IEEE Transactions on Signal Processing, vol. 65, no. 10, pp. 2745-2740, 2017.

Y. Yang, B. Bai, W. Chen, "Spectrum reuse ratio in 5G cellular networks: A matrix graph approach" (Link), IEEE Transactions on Mobile Computing, vol. 16, no. 12, pp. 3541-3533, 2017.

S. Chen, Y. Yang, J. Kovačević, C. Faloutsos, "Monitoring Manhattan's traffic from 5 cameras?", 5th International Workshop on Urban Computing Workshop in ACM KDD 2016 Conference.

S. Chen, Y. Yang, S. Zong, A. Singh, J. Kovačević. "Signal detection on graphs: Bernoilli noise model", GlobalSIP, 2016.

Designing robust ML algorithms using error-correcting codes.

My thesis.

V. Gupta, D. Carrano, Y. Yang, V. Shankar, T. Courtade, K. Ramchandran, "Serverless straggler mitigation using local error-correcting codes" (Full Version, code), ICDCS 2020 (best paper finalist)

S. Dutta*, H. Jeong*, Y. Yang*, V. Cadambe, T. M. Low and P. Grover, "Addressing unreliability in emerging devices and non-von Neumann architectures using coded computing", Proceedings of the IEEE, vol. 108, no. 8, pp. 1219 - 1234, Aug 2020.

Y. Yang*, J. Chung*, G. Wang, V. Gupta, A. Karnati, K. Jiang, I. Stoica, J. E. Gonzalez, K. Ramchandran, "Robust class parallelism: Error-resilient parallel inference with low communication cost", Asilomar 2020 (invited paper).

H. Jeong, Y. Yang, C. Engelmann, V. Gupta, T. M. Low, P. Grover, V. Cadambe and K. Ramchandranan, "3D coded SUMMA: Communication-efficient and robust parallel matrix multiplication", Euro-Par 2020.

Y. Yang, M. Interlandi, P. Grover, S. Kar, A. Saeed, M. Weimer, "Coded elastic computing" (Full Version, code), ISIT 2019.

H. Jeong, Y. Yang and P. Grover, "Systematic matrix multiplication codes", ISIT 2019.

Y. Yang, S. Chen, M. Maddah-Ali, P. Grover, S. Kar, and J. Kovačević, "Fast path localization on graphs via multiscale Viterbi decoding" (Link), IEEE Transactions on Signal Processing, vol. 66, issue 21, pp. 5588-5603, Nov 2018. 

F. Haddadpour, Y. Yang, V. Cadambe, and P. Grover, "Cross-iteration coded computing", Allerton 2018.

U. Sheth, S. Dutta, M. Chaudhari, H. Jeong, Y. Yang, J. Kohonen, T. Roos, P. Grover, "An application of storage-optimal MatDot codes for coded matrix multiplication: Fast k-nearest neighbors estimation", IEEE Big Data 2018.

Y. Yang, P. Grover and S. Kar, "Coding for a single sparse inverse problem" (Link, full version), ISIT 2018.

Y. Yang, P. Grover and S. Kar, "Coded distributed computing for inverse problems" (Link), NeurIPS 2017.

Y. Yang, P. Grover, and S. Kar. "Computing linear transformations with unreliable components" (Link, code), IEEE Transactions on Information Theory, vol. 63, no. 6, pp. 3729-3756, 2017.

Y. Yang, P. Grover, and S. Kar. " Rate-distortion for lossy in-network function computation: Information dissipation and sequential reverse water-filling" (Link), IEEE Transactions on Information Theory, vol. 63, no. 8, pp. 5179-5206, 2017.

Y. Yang, S. Kar, and P. Grover. " Graph codes for distributed instant message collection in an arbitrary noisy broadcast network" (Link), IEEE Transactions on Information Theory, vol. 63, no. 9, pp. 1-26, 2017.

Y. Yang, S. Chen, M. Maddah-Ali, P. Grover, S. Kar and J. Kovačević, "Fast path localization on graphs via multiscale Viterbi decoding", ICASSP 2017.

Y. Yang, P. Grover, and S. Kar. "Coding for lossy in-network function computation: Analyzing sequential function computation with distortion accumulation", ISIT 2016.

Y. Yang, S. Kar, and P. Grover. "Energy-efficient distributed coding for data collection in a noisy sparse network ", ISIT 2016.

Y. Yang, P. Grover, and S. Kar. " Fault-tolerant parallel linear filtering using compressive sensing", ISTC 2016.

Y. Yang, S. Kar, and P. Grover. "Computing linear transforms with unreliable components ", ISIT 2016.

Y. Yang, P. Grover, and S. Kar. "Fault-tolerant distributed logistic regression using unreliable components", Allerton 2016.

Y. Yang, P. Grover, and S. Kar. "Information dissipation in noiseless lossy in-network function computation", IEEE Allerton 2015.

Y. Yang, P. Grover, and S. Kar. "Can a noisy encoder be used to communicate reliably", IEEE Allerton 2014.