Nikolay Malkin

Laurence Perreault-Levasseur

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Pablo Lemos

Sammy N. Sharief

Nikolay Malkin

Yashar Hezaveh

We propose a comprehensive sample-based method for assessing the quality of generative models. The proposed approach enables the estimation … (see more)of the probability that two sets of samples are drawn from the same distribution, providing a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models trained on the same dataset. This comparison can be conducted by dividing the space into non-overlapping regions and comparing the number of data samples in each region. The method only requires samples from the generative model and the test data. It is capable of functioning directly on high-dimensional data, obviating the need for dimensionality reduction. Significantly, the proposed method does not depend on assumptions regarding the density of the true distribution, and it does not rely on training or fitting any auxiliary models. Instead, it focuses on approximating the integral of the density (probability mass) across various sub-regions within the data space.

2024-02-06

ArXiv (preprint)

Amortizing intractable inference in large language models

Edward J Hu

Moksh J. Jain

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This l… (see more)imits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many tasks of interest -- including sequence continuation, infilling, and other forms of constrained generation -- involve sampling from intractable posterior distributions. We address this limitation by using amortized Bayesian inference to sample from these intractable posteriors. Such amortization is algorithmically achieved by fine-tuning LLMs via diversity-seeking reinforcement learning algorithms: generative flow networks (GFlowNets). We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem and demonstrate that our approach enables data-efficient adaptation of LLMs to tasks that require multi-step rationalization and tool use.

2024-01-16

ICLR.cc/2024/Conference (oral)

Delta-AI: Local objectives for amortized inference in sparse graphical models

Jean-Pierre R. Falet

Hae Beom Lee

Chen Sun

We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call …

2024-01-16

ICLR.cc/2024/Conference (poster)

Expected flow networks in stochastic environments and two-player zero-sum games

Bilun Sun

2024-01-16

ICLR.cc/2024/Conference (poster)

PhyloGFN: Phylogenetic inference with generative flow networks

Ming Yang Zhou

Zichao Yan

Elliot Layne

Moksh J. Jain

2024-01-16

ICLR.cc/2024/Conference (poster)

On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling

Minsu Kim

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We ben… (see more)chmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at https://github.com/GFNOrg/gfn-diffusion as a base for future work on diffusion models for amortized inference.

2024-01-01

NeurIPS (published)

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Alexander Tong

Nikolay Malkin

Kilian FATRAS

Lazar Atanackovic

Yanlei Zhang

Guillaume Huguet

Guy Wolf

Yoshua Bengio

We present simulation-free score and flow matching ([SF]…

2024-01-01

AISTATS (published)

Laurence Perreault-Levasseur

Improving Gradient-guided Nested Sampling for Posterior Inference

Will Handley

We present a performant, general-purpose gradient-guided nested sampling algorithm, …

2023-12-06

ArXiv (preprint)

Discrete, compositional, and symbolic representations through attractor dynamics

Andrew Nam

Chen Sun

Compositionality is an important feature of discrete symbolic systems, such as language and programs, as it enables them to have infinite ca… (see more)pacity despite a finite symbol set. It serves as a useful abstraction for reasoning in both cognitive science and in AI, yet the interface between continuous and symbolic processing is often imposed by fiat at the algorithmic level, such as by means of quantization or a softmax sampling step. In this work, we explore how discretization could be implemented in a more neurally plausible manner through the modeling of attractor dynamics that partition the continuous representation space into basins that correspond to sequences of symbols. Building on established work in attractor networks and introducing novel training methods, we show that imposing structure in the symbolic space can produce compositionality in the attractor-supported representation space of rich sensory inputs. Lastly, we argue that our model exhibits the process of an information bottleneck that is thought to play a role in conscious experience, decomposing the rich information of a sensory input into stable components encoding symbolic information.

2023-10-27

NeurIPS.cc/2023/Workshop/InfoCog (oral)

PhyloGFN: Phylogenetic inference with generative flow networks

Ming Yang Zhou

Zichao Yan

Elliot Layne

Moksh J. Jain

Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history a… (see more)nd numerous applications notwithstanding, inference of phylogenetic trees from sequence data remains challenging: the high complexity of tree space poses a significant obstacle for the current combinatorial and probabilistic techniques. In this paper, we adopt the framework of generative flow networks (GFlowNets) to tackle two core problems in phylogenetics: parsimony-based and Bayesian phylogenetic inference. Because GFlowNets are well-suited for sampling complex combinatorial structures, they are a natural choice for exploring and sampling from the multimodal posterior distribution over tree topologies and evolutionary distances. We demonstrate that our amortized posterior sampler, PhyloGFN, produces diverse and high-quality evolutionary hypotheses on real benchmark datasets. PhyloGFN is competitive with prior works in marginal likelihood estimation and achieves a closer fit to the target distribution than state-of-the-art variational inference methods. Our code is available at https://github.com/zmy1116/phylogfn.

2023-10-12

ArXiv (preprint)

Amortizing intractable inference in large language models

Edward J Hu

Moksh J. Jain

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This l… (see more)imits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many tasks of interest -- including sequence continuation, infilling, and other forms of constrained generation -- involve sampling from intractable posterior distributions. We address this limitation by using amortized Bayesian inference to sample from these intractable posteriors. Such amortization is algorithmically achieved by fine-tuning LLMs via diversity-seeking reinforcement learning algorithms: generative flow networks (GFlowNets). We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem and demonstrate that our approach enables data-efficient adaptation of LLMs to tasks that require multi-step rationalization and tool use.

2023-10-06

ArXiv (preprint)