6 papers
Lossy Compression, Realism, and Coordination
Yassine Hamdi, Deniz Gündüz
Classical rate-distortion theory characterizes the fundamental limits of lossy compression under fidelity constraints, but minimizing distortion often yields perceptually unsatisfy…
Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
Yanxiao Liu, Yijun Fan, Deniz Gündüz
Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic…
The Rate-Distortion-Perception Trade-Off with Algorithmic Realism
Yassine Hamdi, Aaron B. Wagner, Deniz Gündüz
Realism constraints (or constraints on perceptual quality) have received considerable recent attention within the context of lossy compression, particularly of images. Theoretical…
Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality
Arpan Mukherjee, Marcello Bullo, Debabrota Basu +1
While test-time scaling with verification has shown promise in improving the performance of large language models (LLMs), the role of the verifier and its imperfections remain unde…
SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
Arpan Mukherjee, Marcello Bullo, Deniz Gündüz
Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity…
Rate-Distortion-Perception Trade-off with Strong Realism Constraints: Role of Side Information and Common Randomness
Yassine Hamdi, Aaron B. Wagner, Deniz Gündüz
In image compression, with recent advances in generative modeling, existence of a trade-off between the rate and perceptual quality has been brought to light, where the perceptual…