Research output per year
Research output per year
Fingerprint
Dive into the research topics where Michael Murray is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
Research output
-
Benign overfitting in leaky ReLU networks with moderate input dimension
Karhadkar, K., George, E., Murray, M., Montúfar, G. & Needell, D., 15 Dec 2024, Advances in Neural Information Processing Systems 37: (NeurIPS 2024). NeurIPS Proceedings, 49 p. (NeurIPS Proceedings).Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding
Open Access -
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Karhadkar, K., Murray, M. & Montúfar, G., 10 Dec 2024, The Thirty-eighth Annual Conference on Neural Information Processing Systems. NeurIPS Proceedings, Vol. 37. 53 p. (Advances in Neural Information Processing Systems).Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding
Open Access2 Link opens in a new tab Citations (SciVal) -
Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape
Karhadkar, K., Murray, M., Tseran, H. & Montúfar, G., 4 Jun 2024, In: Transactions on Machine Learning Research. 2024Research output: Contribution to journal › Article › peer-review
Open Access3 Link opens in a new tab Citations (SciVal) -
Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?
George, E., Murray, M., Swartworth, W. & Needell, D., 16 Dec 2023, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023). NeurIPS Proceedings, 51 p.Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding
Open Access -
Activation function design for deep networks: linearity and effective initialisation
Murray, M., Abrol, V. & Tanner, J., 31 Jul 2022, In: Applied and Computational Harmonic Analysis. 59, p. 117-154 38 p.Research output: Contribution to journal › Article › peer-review
Open Access20 Link opens in a new tab Citations (SciVal)
-
SIAM Annual Meeting
Murray, M. (Speaker)
8 Jul 2024 → 12 Jul 2024Activity: Academic conferences and events (excluding conference publications) › Conference presentation / attendance
-
11th International Conference on Learning Representations
Murray, M. (Speaker)
1 May 2023 → 5 May 2023Activity: Academic conferences and events (excluding conference publications) › Conference presentation / attendance
-
11th International Conference on Learning Representations (Event)
Murray, M. (Peer reviewer)
1 May 2023 → 5 May 2023Activity: Publication peer-review and editorial roles › Publication peer review
-
Conference on Mathematics of Machine Learning
Murray, M. (Speaker)
22 Aug 2025 → 25 Sept 2025Activity: Academic conferences and events (excluding conference publications) › Conference presentation / attendance
-
37th Conference on Neural Information Processing Systems, NeurIPS 2023 (Event)
Murray, M. (Peer reviewer)
10 Dec 2023 → 16 Dec 2023Activity: Publication peer-review and editorial roles › Publication peer review