77 citations · 732 across the 55 of their papers we have counts for
59 papers
Attribute Controlled Dialogue Prompting
Runcheng Liu, Ahmad Rashid, Ivan Kobyzev +2
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and…
An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
Yudong Luo, Guiliang Liu, Pascal Poupart +1
Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Tra…
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization
Aref Jafari, Ivan Kobyzev, Mehdi Rezagholizadeh +2
Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowl…
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…
Learning Functions on Multiple Sets using Multi-Set Transformers
Kira Selby, Ahmad Rashid, Ivan Kobyzev +2
We propose a general deep architecture for learning functions on multiple permutation-invariant sets. We also show how to generalize this architecture to sets of elements of any di…
Robust One Round Federated Learning with Predictive Space Bayesian Inference
Mohsin Hasan, Zehao Zhang, Kaiyang Guo +4
Making predictions robust is an important challenge. A separate challenge in federated learning (FL) is to reduce the number of communication rounds, particularly since doing so re…