IFML Seminar
IFML Seminar: 11/07/25 - Model Self-improvement via Optimal Retraining
Abstract: Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model’s performance. While prior works have demonstrated the benefits of specific heuristic...
Upcoming Events
Past Events
- October2512:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Reinforcement learning often faces a trade-off between model flexibility and computational tractability. Flexible models can capture complex…
- October1712:15 - 1 pm
IFML Seminar
Event DetailsAbstract: I will argue that deep networks work well because of a characteristic structure in the space of learnable tasks...
- October412:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Sequential decision-making (SDM) is crucial for adapting machine learning to dynamic real-world scenarios such as fluctuating markets or evolving…
- September2712:15 - 1 pm
IFML Seminar
Event DetailsAbstract: One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates...
- September1312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: We consider the problem of model selection in a high-dimensional sparse linear regression model under privacy constraints. We propose...
- September612:15 - 1 pm
IFML Seminar
Event DetailsAbstract: From the moment we open our eyes, we are surrounded by people. By observing the people around us, we...
