✅ Lossless Bounds

Compression Limits, Perfect Reconstruction, Information Theory, Entropy Coding

Joint Time-Position Statistics and Fisher Information in Drift-Diffusion Molecular Channels
arxiv.org·5h
📡Information theory
Why Stacking Sliding Windows Can't See Far
guangxuanx.com·4h·
Discuss: Hacker News
🧮Kolmogorov Complexity
Positional Embeddings in Transformers: A Math Guide to RoPE & ALiBi
towardsdatascience.com·19h
📐Geometric Hashing
BW21-CBV-Kit——Home Video Monitoring and Playback System
hackster.io·3h
🎬Video Codecs
Enclosures that minimize the sum of area and perimeter
11011110.github.io·1d
📊Computational Geometry
DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
arxiv.org·5h
⧗Information Bottleneck
Paying attention to feature distribution alignment (pun intended)
alexshtf.github.io·2d·
Discuss: Hacker News
📐Linear Algebra
k-NN Classification and Model Evaluation
dev.to·1d·
Discuss: DEV
🧠Machine Learning
How much power does gzip save on IoT web access?
bitbanksoftware.blogspot.com·1d·
Discuss: Lobsters, Hacker News
📦Deflate
Convergence and Generalization of Anti-Regularization for Parametric Models
arxiv.org·1d
🧠Machine Learning
Learn You a NeRF
peterstefek.me·6h·
Discuss: Hacker News
📟Terminal Physics
Drama Model Inference Efficiency Boosted by 1.7x-2.3x
pytorch.org·9h·
Discuss: Hacker News
🚀SIMD Text Processing
Das Problem mit German Strings
polarsignals.com·12h·
Discuss: Lobsters, Hacker News
✅Format Verification
E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
arxiv.org·1d
🧠Machine Learning
Learning ON Large Datasets Using Bit-String Trees
arxiv.org·1d
🗂️Vector Databases
HV Metric For Time-Domain Full Waveform Inversion
arxiv.org·1d
📊Rate-Distortion Theory
Adversarial Examples Are Not Bugs, They Are Superposition
livgorton.com·14h·
Discuss: Hacker News
🧠Machine Learning
Distance-informed Neural Processes
arxiv.org·5h
🧠Machine Learning
TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning
arxiv.org·1d
🗂️Vector Databases
Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
arxiv.org·1d
⧗Information Bottleneck