Profiles2024-2026
Rajiv Khanna
Purdue University
11Papers
10Last author
14Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- Sharpness-Aware Machine UnlearningAuthor 2 of 2ICLR 2026 · 10 citations
- Membership Privacy Risks of Sharpness Aware MinimizationAuthor 5 of 5ICLR 2026 · 3 citations
- Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI CollaborationAuthor 3 of 3AAAI 2026
- From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?Author 5 of 6ACL Findings 2026
- A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity BiasAuthor 2 of 2NeurIPS 2025 · 3 citations
- Structure-Aware Spectral Sparsification via Uniform Edge SamplingAuthor 3 of 3NeurIPS 2025 · 1 citation
- On the Support Vector Effect in DNNs: Rethinking Data Selection and AttributionAuthor 4 of 4KDD 2025
- Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss LandscapesAuthor 2 of 2NeurIPS 2025
- A Precise Characterization of SGD Stability Using Loss Surface GeometryAuthor 6 of 6ICLR 2024 · 2 citations
- The Space Complexity of Approximating Logistic LossAuthor 3 of 3NeurIPS 2024 · 1 citation
- Approximating Memorization Using Loss Surface Geometry for Dataset Pruning and SummarizationAuthor 3 of 3KDD 2024
