HS
Hanie Sedghi
cs.LGstat.MLcs.AIcs.CVcs.CLcs.NEmath.STstat.THcs.CYcs.DB
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
33 papers in the corpus · 2014–2025Statistical Structure Learning, Towards a Robust Smart Grid1403.1863v1 · Hanie Sedghi, Edmond Jonckheere2014 · 3 citationsarXiv
Enhancing LLM Planning Capabilities through Intrinsic Self-Critique2512.24103v1 · Bernd Bohnet, Pierre-Alexandre Kamienny, Hanie Sedghi et al.2025 · 0 citationsarXiv
Improving Large Language Model Planning with Action Sequence Similarity2505.01009v1 · Xinran Zhao, Hanie Sedghi, Bernd Bohnet et al.2025 · 0 citationsThe Thirteenth International Conference on Learning Representations (ICLR 2025)
Exploring and Benchmarking the Planning Capabilities of Large Language Models2406.13094v2 · Bernd Bohnet, Azade Nova, Aaron T Parisi et al.2024 · 1 citationarXiv
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability2408.07852v1 · Jiri Hron, Laura Culp, Gamaleldin Elsayed et al.2024 · 2 citationsarXiv
Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation2406.00179v1 · Bernd Bohnet, Kevin Swersky, Rosanne Liu et al.2024 · 0 citationsarXiv
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models2312.06585v4 · Avi Singh, John D. Co-Reyes, Rishabh Agarwal et al.2023 · 7 citationsarXiv
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?2311.07587v2 · C. Daniel Freeman, Laura Culp, Aaron Parisi et al.2023 · 0 citationsarXiv
REPAIR: REnormalizing Permuted Activations for Interpolation Repair2211.08403v3 · Keller Jordan, Hanie Sedghi, Olga Saukh et al.2022 · 11 citationsarXiv
Can Neural Network Memorization Be Localized?2307.09542v1 · Pratyush Maini, Michael C. Mozer, Hanie Sedghi et al.2023 · 1 citationarXiv
The Role of Pre-training Data in Transfer Learning2302.13602v2 · Rahim Entezari, Mitchell Wortsman, Olga Saukh et al.2023 · 8 citationsarXiv
Leveraging Unlabeled Data to Track Memorization2212.04461v1 · Mahsa Forouzesh, Hanie Sedghi, Patrick Thiran2022 · 0 citationsarXiv
Layer-Stack Temperature Scaling2211.10193v1 · Amr Khalifa, Michael C. Mozer, Hanie Sedghi et al.2022 · 0 citationsarXiv
Teaching Algorithmic Reasoning via In-context Learning2211.09066v1 · Hattie Zhou, Azade Nova, Hugo Larochelle et al.2022 · 23 citationsarXiv
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance2201.04234v3 · Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton et al.2022 · 19 citationsarXiv
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks2110.06296v2 · Rahim Entezari, Hanie Sedghi, Olga Saukh et al.2021 · 17 citationsarXiv
Understanding the effect of sparsity on neural networks robustness2206.10915v1 · Lukas Timpl, Rahim Entezari, Hanie Sedghi et al.2022 · 3 citationsarXiv
Exploring the Limits of Large Scale Pre-training2110.02095v1 · Samira Abnar, Mostafa Dehghani, Behnam Neyshabur et al.2021 · 33 citationsarXiv
Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent2106.06080v2 · Samira Abnar, Rianne van den Berg, Golnaz Ghiasi et al.2021 · 4 citationsarXiv
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers2010.08127v2 · Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi2020 · 20 citationsarXiv
What is being transferred in transfer learning?2008.11687v2 · Behnam Neyshabur, Hanie Sedghi, Chiyuan Zhang2020 · 230 citationsNeurIPS 2020
Generalization bounds for deep convolutional neural networks1905.12600v6 · Philip M. Long, Hanie Sedghi2019 · 45 citationsarXiv
On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network.31614106 · Long, Philip M, Sedghi, Hanie2020 · 3 citationsNeural computation. 2019;31(12):2562-2580
The intriguing role of module criticality in the generalization of deep networks1912.00528v3 · Niladri S. Chatterji, Behnam Neyshabur, Hanie Sedghi2019 · 25 citationsarXiv
MLSys: The New Frontier of Machine Learning Systems1904.03257v3 · Alexander Ratner, Dan Alistarh, Gustavo Alonso et al.2019 · 20 citationsarXivon Valency
The Singular Values of Convolutional Layers1805.10408v2 · Hanie Sedghi, Vineet Gupta, Philip M. Long2018 · 137 citationsarXiv
On the effect of the activation function on the distribution of hidden nodes in a deep network1901.02104v1 · Philip M. Long, Hanie Sedghi2019 · 4 citationsarXiv
Knowledge Completion for Generics using Guided Tensor Factorization1612.03871v3 · Hanie Sedghi, Ashish Sabharwal2016 · 5 citationsarXiv
Training Input-Output Recurrent Neural Networks through Spectral Methods1603.00954v5 · Hanie Sedghi, Anima Anandkumar2016 · 11 citationsarXiv
Provable Tensor Methods for Learning Mixtures of Generalized Linear Models1412.3046v4 · Hanie Sedghi, Majid Janzamin, Anima Anandkumar2014 · 11 citationsarXiv
Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods1506.08473v3 · Majid Janzamin, Hanie Sedghi, Anima Anandkumar2015 · 132 citationsarXiv
Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decomposition1402.5131v6 · Hanie Sedghi, Anima Anandkumar, Edmond Jonckheere2014 · 0 citationsarXiv
Score Function Features for Discriminative Learning: Matrix and Tensor Framework1412.2863v2 · Majid Janzamin, Hanie Sedghi, Anima Anandkumar2014 · 29 citationsarXiv
Career total: 52 works. 33 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.