4 papers
Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings
Sreejith Sreekumar, Nir Weinberger
Maximum likelihood prediction (MLP) is a core task at the heart of modern large language models. Here, we study a quantum version of this task for a simplified data model consistin…
Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
Ilay Yavlovich, Jad Agbaria, Muhamed Mhamed +2
The Linear Assignment Problem is a fundamental combinatorial optimization task where classical exact solvers ensure optimality but suffer from an bottleneck, w…
Exploration-Exploitation Tradeoff in Universal Lossy Compression
Nir Weinberger, Ram Zamir
Universal compression can learn the source and adapt to it either in a batch mode (forward adaptation), or in a sequential mode (backward adaptation). We recast the sequential mode…
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
Chen Zeno, Hila Manor, Greg Ongie +3
While diffusion models generate high-quality images via probability flow, the theoretical understanding of this process remains incomplete. A key question is when probability flow…