Search Results for author: Marcin Sendera

Found 10 papers, 7 papers with code

High-Fidelity Transfer of Functional Priors for Wide Bayesian Neural Networks by Learning Activations

1 code implementation21 Oct 2024 Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk

Function-space priors in Bayesian Neural Networks provide a more intuitive approach to embedding beliefs directly into the model's output, thereby enhancing regularization, uncertainty quantification, and risk-aware decision-making.

Decision Making Model Selection +1

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models

1 code implementation4 Oct 2024 Artur Kasymov, Marcin Sendera, Michał Stypułkowski, Maciej Zięba, Przemysław Spurek

To solve this issue, we introduce AutoLoRA, a novel guidance technique for diffusion models fine-tuned with the LoRA approach.

Diversity

Amortizing intractable inference in diffusion models for vision, language, and control

1 code implementation31 May 2024 Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem.

continuous-control Continuous Control +3

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

1 code implementation9 Feb 2024 Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong

Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.

Denoising Efficient Exploration

Improved off-policy training of diffusion samplers

1 code implementation7 Feb 2024 Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function.

Benchmarking

Flow-based SVDD for anomaly detection

no code implementations10 Aug 2021 Marcin Sendera, Marek Śmieja, Łukasz Maziarka, Łukasz Struski, Przemysław Spurek, Jacek Tabor

We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools.

Anomaly Detection One-class classifier

Data adaptation in HANDY economy-ideology model

no code implementations8 Apr 2019 Marcin Sendera

However, despite their ability to better forecasting, the problem of an appropriate fitting ground truth data to those, high-dimensional and nonlinear models seems to be inevitable.

Cannot find the paper you are looking for? You can Submit a new open access paper.