11 citations · 22 across the 10 of their papers we have counts for
10 papers
Gradient Prediction with Control Variates in the Cheap-Forward Regime
Kamil Ciosek, Nicolò Felicioni, Juan Elenter +1
We study whether otherwise-idle inference resources could reduce the scarce-GPU cost of training. Our analysis uses a simulated compute ledger in which fleet work is billed at a fr…
Investigating the Histogram Loss in Regression
Ehsan Imani, Kai Luedemann, Sam Scholnick-Hughes +2
It is becoming increasingly common in regression to train neural networks that model the entire distribution even if only the mean is required for prediction. This additional model…
The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani +3
Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representa…
Label Alignment Regularization for Distribution Shift
Ehsan Imani, Guojun Zhang, Runjia Li +4
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular v…
Representation Alignment in Neural Networks
Ehsan Imani, Wei Hu, Martha White
It is now a standard for neural network representations to be trained on large, publicly available datasets, and used for new problems. The reasons for why neural network represent…
Off-Policy Actor-Critic with Emphatic Weightings
Eric Graves, Ehsan Imani, Raksha Kumaraswamy +1
A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. T…
Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
Farzane Aminmansour, Taher Jafferjee, Ehsan Imani +3
Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environme…
An implicit function learning approach for parametric modal regression
Yangchen Pan, Ehsan Imani, Martha White +1
For multi-valued functions---such as when the conditional distribution on targets given the inputs is multi-modal---standard regression approaches are not always desirable because…
An Off-policy Policy Gradient Theorem Using Emphatic Weightings
Ehsan Imani, Eric Graves, Martha White
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorit…
Improving Regression Performance with Distributional Losses
Ehsan Imani, Martha White
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classificat…