18 citations · 45 across the 21 of their papers we have counts for
21 papers
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
Gergely Flamich, Oykü Sıla Güner, Yanxiao Liu +1
The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity. Differential privacy (D…
Multi-Marginal Couplings for Metropolis-Hastings
Buu Phan, Gergely Flamich, Ashish Khisti +1
Convergence diagnosis for Markov chain Monte Carlo is a matter of fundamental importance in computational statistics: it determines the resources allocated to a particular sampling…
Singular Relative Entropy Coding with Bits-Back Rejection Sampling
Gergely Flamich, Spencer Hill
A relative entropy code for a source is a stochastic code that encodes random samples from a prescribed using as few bits as possible. A generalisation…
Rejection Sampling is Optimal for Relative Entropy Coding
Spencer Hill, Fady Alajaji, Tamás Linder +1
In relative entropy coding, a sender aims to design a stochastic code such that, on input , the receiver can generate a sample . It is a standard r…
Data Compression with Stochastic Codes
Gergely Flamich, Deniz Gündüz
Machine learning has had a major impact on data compression over the last decade and opened up many new theoretical and applied fields of inquiry. This paper describes one such dir…
Data Compression with Relative Entropy Coding
Gergely Flamich
Over the last few years, machine learning unlocked previously infeasible features for compression, such as providing guarantees for users' privacy or tailoring compression to speci…
You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation
Gergely Flamich, David Vilar, Jan-Thorsten Peter +1
The goal of translation, be it by human or by machine, is, given some text in a source language, to produce text in a target language that simultaneously 1) preserves the meaning o…
The Redundancy of Non-Singular Channel Simulation
Gergely Flamich, Sharang M. Sriramu, Aaron B. Wagner
Channel simulation is an alternative to quantization and entropy coding for performing lossy source coding. Recently, channel simulation has gained significant traction in both the…
Getting Free Bits Back from Rotational Symmetries in LLMs
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these ne…
Some Notes on the Sample Complexity of Approximate Channel Simulation
Gergely Flamich, Lennie Wells
Channel simulation algorithms can efficiently encode random samples from a prescribed target distribution and find applications in machine learning-based lossy data compression…
Accelerating Relative Entropy Coding with Space Partitioning
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Relative entropy coding (REC) algorithms encode a random sample following a target distribution , using a coding distribution shared between the sender and receiver. Sadly,…
On Channel Simulation with Causal Rejection Samplers
Daniel Goc, Gergely Flamich
One-shot channel simulation has recently emerged as a promising alternative to quantization and entropy coding in machine-learning-based lossy data compression schemes. However, wh…
Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo
Szilvia Ujváry, Gergely Flamich, Vincent Fortuin +1
An important yet underexplored question in the PAC-Bayes literature is how much tightness we lose by restricting the posterior family to factorized Gaussian distributions when opti…
Faster Relative Entropy Coding with Greedy Rejection Coding
Gergely Flamich, Stratis Markou, Jose Miguel Hernandez Lobato
Relative entropy coding (REC) algorithms encode a sample from a target distribution using a proposal distribution using as few bits as possible. Unlike entropy coding, REC…
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
Jiajun He, Gergely Flamich, Zongyu Guo +1
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representatio…
Minimal Random Code Learning with Mean-KL Parameterization
Jihao Andreas Lin, Gergely Flamich, José Miguel Hernández-Lobato
This paper studies the qualitative behavior and robustness of two variants of Minimal Random Code Learning (MIRACLE) used to compress variational Bayesian neural networks. MIRACLE…
Compression with Bayesian Implicit Neural Representations
Zongyu Guo, Gergely Flamich, Jiajun He +2
Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image. Based on this view,…
Greedy Poisson Rejection Sampling
Gergely Flamich
One-shot channel simulation is a fundamental data compression problem concerned with encoding a single sample from a target distribution using a coding distribution using a…
Adaptive Greedy Rejection Sampling
Gergely Flamich, Lucas Theis
We consider channel simulation protocols between two communicating parties, Alice and Bob. First, Alice receives a target distribution , unknown to Bob. Then, she employs a shar…
Fast Relative Entropy Coding with A* coding
Gergely Flamich, Stratis Markou, José Miguel Hernández-Lobato
Relative entropy coding (REC) algorithms encode a sample from a target distribution using a proposal distribution , such that the expected codelength is $\mathcal{O}(D_{KL}[…
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato
Variational Autoencoders (VAEs) have seen widespread use in learned image compression. They are used to learn expressive latent representations on which downstream compression meth…