PQMass provides a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models and scales well to moderately high-dimensional data and thus obviates the need for feature extraction in practical applications.
Pablo Lemos, S. Sharief, Esmeralda S. Whitammer et al.· International Conference on...· 10 citations
This paper proposes a novel flow matching method that overcomes the limitations of existing multi-marginal trajectory inference algorithms, using a GAN-inspired adversarial loss to fit neurally parametrised interpolant curves between source and target points such that the marginal distributions at intermediate time points are close to the observed distributions.
Oskar Kviman, Kirill Tamogashev, Nicola Branchini et al.· arXiv.org· 2 citations
This paper proposes the first general method for modelling Schr\"odinger bridges when one (or both) distributions are given by their unnormalised densities, with no access to data samples, and applies the newly developed algorithm to the problem of sampling posterior distributions in latent spaces of generative models, thus creating a data-free image-to-image translation method.
Kirill Tamogashev, Esmeralda S. Whitammer· arXiv.org· 4 citations
A novel unified operator is introduced that combines several regularized RL operators into a general framework that better targets peakier sampling distributions and is named trajectory general mellowmax (TGM), which is shown to identify higher quality, diverse candidates than baselines in both synthetic and real-world tasks.
Marco Jiralerspong, Esther Derman, Danilo Vucetic et al.· 2 citations
The teacher, an auxiliary behavior model, is trained to sample high-loss regions of the student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum.
Minsu Kim, Sanghyeok Choi, Taeyoung Yun et al.· International Conference on...· 27 citations· ⚡6
This work interprets chain-of-thought reasoning as a latent variable modeling problem and demonstrates that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization.
Edward J. Hu, Moksh Jain, Eric Elmoznino et al.· International Conference on...· 110 citations· ⚡19
This work shows that EFlowNets outperform other GFlowNet formulations in stochastic tasks such as protein design and extends the concept of EflowNets to adversarial environments, proposing adversarial flow networks (A FlowNets) for two-player zero-sum games.
Marco Jiralerspong, Bilun Sun, Danilo Vucetic et al.· International Conference on...· 11 citations· ⚡1
A new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) is presented that enables off-policy training but avoids the need to instantiate all the random variables for each parameter update, thus speeding up training considerably.
J. Falet, Haebeom Lee, Esmeralda S. Whitammer et al.· International Conference on...· 9 citations
This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs. We demonstrate that, in certain cases, VI algorithms are equivalent to special cases of GFlowNets in the sense of equality of expected gradients of their learning objectives. We then point out the differences between the two families and show how these differences emerge experimentally. Notably, GFlowNets, which borrow ideas from reinforcement learning, are more amenable than VI to off-policy training without the cost of high gradient variance induced by importance sampling. We argue that this property of GFlowNets can provide advantages for capturing diversity in multimodal target distributions.
Esmeralda S. Whitammer, S. Lahlou, T. Deleu et al.· International Conference on...· 120 citations· ⚡9
Amortized sampling of the posterior over data is studied, and the asymptotic correctness of a data-free learning objective, relative trajectory balance, is proved for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases.
S. Venkatraman, Moksh Jain, Luca Scimeca et al.· Neural Information Processin...· 75 citations· ⚡5
This work benchmarks several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks), and proposes a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer.
Marcin Sendera, Minsu Kim, Sarthak Mittal et al.· Neural Information Processin...· 52 citations· ⚡7
This paper proposes a method to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions, using a single GFlowNet whose sampling policy follows a two-phase process.
T. Deleu, Mizu Nishikawa-Toomey, Jithendaraa Subramanian et al.· Neural Information Processin...· 65 citations· ⚡4
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
