Generalization and Personalization in Federated Learning - Karan Singhal
Explore generalization and personalization in federated learning, focusing on medical AI applications. Insights on improving model performance across diverse data distributions and healthcare settings.
On Building General, Zero-Shot Robot Policies - EI Seminar
Explore the development of zero-shot robot policies for real-world tasks. Gain insights into Robot Utility Models (RUMs) and their ability to generalize to new environments without finetuning, achieving 90% success in novel settings.
Stochastic Learning Dynamics and Generalization in Neural Networks
Explore stochastic learning dynamics and generalization in neural networks, uncovering key insights into their behavior and performance in various applications.
COMI: Correct and Mitigate Shortcut Learning Behavior in Deep Neural Networks
Explore techniques to correct and mitigate shortcut learning in deep neural networks, enhancing model robustness and generalization capabilities.
Infinite Limits and Scaling Laws of Neural Networks
Explore infinite parameter limits of deep neural networks, scaling laws, and their impact on performance. Gain insights into representation learning and computational resource optimization for neural network training.
Comparison and Transfer Between Tasks in Overparameterized Learning
Explore similarities and differences in classification and regression tasks for overparameterized linear models. Gain insights into task transfer and generalization in high-dimensional regimes.
The Dynamics of Memorization and Generalization in Deep Learning
Explore the complex interplay between memorization and generalization in deep learning models, examining strategies to mitigate unwanted memorization and the impact of pruning techniques on learning outcomes.
Two Stories in Mechanistic Interpretation of Natural and Artificial Neural Computation
Explore two stories in mechanistic interpretation of neural computation, covering in-context learning in Transformers and insights into linear regression tasks using linear attention models.
Dynamics of Brain's Deep Network
Uncover insights into brain's deep network processing of visual information, exploring biophysical principles and emergent theories through cutting-edge neurotechnology and experimental observations.
Neural Networks Meet Nonparametric Regression: Generalization by Weight Decay and Large Learning Rates
Explore the intersection of deep neural networks and nonparametric regression, uncovering insights on overparameterization, representation learning, and adaptive generalization in machine learning.
Generalization in Robotic Behavior Cloning: Pitfalls and Promises
Explore challenges and solutions in robotic behavior cloning, focusing on generalization in continuous state/action spaces. Gain insights into frameworks enabling agents to imitate complex behaviors with provable guarantees.
Know When You Know: Handling Adversarial Data by Abstaining
Explore sequential prediction in stochastic settings with adversarial interference. Learn strategies for handling distribution shifts and making confident predictions while abstaining from uncertain cases.
Does Generalization Imply Accuracy on the Line? A New Look at Robust Generalization
Explore the relationship between generalization and accuracy in machine learning, examining robust generalization through a fresh perspective.
How Well Does Diffusion Model Generate? Exploring Generalization in Emerging Settings
Explore the capabilities and limitations of diffusion models in generative tasks, focusing on emerging generalization settings and their implications.
Generalization in Diffusion Models Arises from Geometry-Adaptive Harmonic Representations
Uncover the geometric foundations of diffusion models' generalization capabilities through adaptive harmonic representations in this insightful exploration.
In-Context Principle Learning from Mistakes
Explore Uri Alon's insights on in-context principle learning from mistakes, focusing on emerging generalization settings in AI and machine learning.
The Pitfalls of Next-token Prediction in Language Models
Explore the limitations of next-token prediction in AI, examining its challenges in modeling human intelligence and potential solutions beyond this paradigm.
When Calibration Goes Awry: Hallucination in Language Models
Explore the phenomenon of hallucinations in language models, their connection to calibration, and potential mitigation strategies in this insightful talk by Adam Kalai from OpenAI.
LLM Metacognition: Understanding and Leveraging "Thinking about Thinking"
Explore LLM metacognition and its impact on AI capabilities. Gain insights into how large language models demonstrate deeper understanding and reasoning about their own skills and learning processes.
Generalization from the Behavioral Perspective
Dive into the behavioral perspective of generalization, exploring emerging settings and their implications in machine learning and data analysis.
Is Optimization the Right Language to Understand Deep Learning? - Sanjeev Arora
Explore deep learning optimization, generalization, and neural tangent kernels with Sanjeev Arora. Gain insights into training wide networks and matrix completion techniques.