Follow
Sarthak Mittal
Title
Cited by
Cited by
Year
A modern take on the bias-variance tradeoff in neural networks
B Neal, S Mittal, A Baratin, V Tantia, M Scicluna, S Lacoste-Julien, ...
arXiv preprint arXiv:1810.08591, 2018
2322018
Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules
S Mittal, A Lamb, A Goyal, V Voleti, M Shanahan, G Lajoie, M Mozer, ...
International Conference on Machine Learning, 6972-6986, 2020
822020
Diffusion-Based Representation Learning
S Mittal, K Abstreiter, S Bauer, B Schölkopf, A Mehrjou
International Conference on Machine Learning, 2023
52*2023
Is a modular architecture enough?
S Mittal, Y Bengio, G Lajoie
Advances in Neural Information Processing Systems 35, 28747-28760, 2022
522022
Systematic evaluation of causal discovery in visual model based reinforcement learning
NR Ke, A Didolkar, S Mittal, A Goyal, G Lajoie, S Bauer, D Rezende, ...
NeurIPS 2021 Datasets and Benchmarks Track, 2021
522021
Iterated denoising energy matching for sampling from boltzmann densities
T Akhound-Sadegh, J Rector-Brooks, AJ Bose, S Mittal, P Lemos, CH Liu, ...
arXiv preprint arXiv:2402.06121, 2024
402024
Amortizing intractable inference in diffusion models for vision, language, and control
S Venkatraman, M Jain, L Scimeca, M Kim, M Sendera, M Hasan, L Rowe, ...
arXiv preprint arXiv:2405.20971, 2024
272024
Compositional Attention: Disentangling Search and Retrieval
S Mittal, SC Raparthy, I Rish, Y Bengio, G Lajoie
The International Conference on Learning Representations (ICLR), 2022, 2021
262021
On neural architecture inductive biases for relational tasks
G Kerg, S Mittal, D Rolnick, Y Bengio, B Richards, G Lajoie
arXiv preprint arXiv:2206.05056, 2022
252022
On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling
M Sendera, M Kim, S Mittal, P Lemos, L Scimeca, J Rector-Brooks, ...
arXiv e-prints, arXiv: 2402.05098, 2024
202024
Improved off-policy training of diffusion samplers
M Sendera, M Kim, S Mittal, P Lemos, L Scimeca, J Rector-Brooks, ...
Advances in Neural Information Processing Systems 37, 81016-81045, 2024
112024
Mixupe: Understanding and improving mixup from directional derivative perspective
Y Zou, V Verma, S Mittal, WH Tang, H Pham, J Kannala, Y Bengio, A Solin, ...
Uncertainty in Artificial Intelligence, 2597-2607, 2023
112023
Amortized In-Context Bayesian Posterior Estimation
S Mittal, NL Bracher, G Lajoie, P Jaini, M Brubaker
arXiv preprint arXiv:2502.06601, 2025
8*2025
A Modern Take on the Bias-Variance Tradeoff in Neural Networks.[arXiv]
B Neal, S Mittal, A Baratin, V Tantia, M Scicluna, S Lacoste-Julien, ...
arXiv preprint arXiv:1810.08591, 2019
82019
From points to functions: Infinite-dimensional representations in diffusion models
S Mittal, G Lajoie, S Bauer, A Mehrjou
arXiv preprint arXiv:2210.13774, 2022
72022
A modern take on the bias-variance tradeoff in neural networks arXiv preprint arXiv: 181008591
B Neal, S Mittal, A Baratin, V Tantia, M Scicluna, S Lacoste-Julien, ...
72018
A modern take on the bias-variance tradeoff in neural networks. arXiv 2018
B Neal, S Mittal, A Baratin, V Tantia, M Scicluna, S Lacoste-Julien, ...
arXiv preprint arXiv:1810.08591, 2018
62018
Steering masked discrete diffusion models via discrete denoising posterior prediction
J Rector-Brooks, M Hasan, Z Peng, Z Quinn, C Liu, S Mittal, N Dziri, ...
arXiv preprint arXiv:2410.08134, 2024
52024
Inductive biases for relational tasks
G Kerg, S Mittal, D Rolnick, Y Bengio, BA Richards, G Lajoie
ICLR2022 Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022
52022
In-context learning and Occam's razor
E Elmoznino, T Marty, T Kasetty, L Gagnon, S Mittal, M Fathi, D Sridhar, ...
arXiv preprint arXiv:2410.14086, 2024
32024
The system can't perform the operation now. Try again later.
Articles 1–20