Generative diffusion models have achieved spectacular performance in many areas of generative modeling. While the fundamental ideas behind these models come from non-equilibrium physics, in this paper we show that many aspects of these models can be understood using the tools of equilibrium statistical mechanics. Using this reformulation, we show that generative diffusion models undergo second-order phase transitions corresponding to symmetry breaking phenomena. We argue that this lead to a form of instability that lies at the heart of their generative capabilities and that can be described by a set of mean field critical exponents. We conclude by analyzing recent work connecting diffusion models and associative memory networks in view of the thermodynamic formulations.
Gaussian processes (GP) regression has gained substantial popularity in machine learning applications. The behavior of a GP regression depends on the choice of covariance function. Stationary covariance functions are favorite in machine learning applications. However, (non-periodic) stationary covariance functions are always mean reverting and can therefore exhibit pathological behavior when applied to data that does not relax to a fixed global mean value. In this paper, we show that it is possible to use improper GP prior with infinite variance to define processes that are stationary but not mean reverting. To this aim, we introduce a large class of improper kernels that can only be defined in this improper regime. Specifically, we introduce the Smooth Walk kernel, which produces infinitely smooth samples, and a family of improper Mat\'ern kernels, which can be defined to be $j$-times differentiable for any integer $j$. The resulting posterior distributions can be computed analytically and it involves a simple correction of the usual formulas. By analyzing both synthetic and real data, we demonstrate that these improper kernels solve some known pathologies of mean reverting GP regression while retaining most of the favourable properties of ordinary smooth stationary kernels.
Hopfield networks are widely used in neuroscience as simplified theoretical models of biological associative memory. The original Hopfield networks store memories by encoding patterns of binary associations, which result in a synaptic learning mechanism known as Hebbian learning rule. Modern Hopfield networks can achieve exponential capacity scaling by using highly non-linear energy functions. However, the energy function of these newer models cannot be straightforwardly compressed into binary synaptic couplings and it does not directly provide new synaptic learning rules. In this work we show that generative diffusion models can be interpreted as energy-based models and that, when trained on discrete patterns, their energy function is equivalent to that of modern Hopfield networks. This equivalence allows us to interpret the supervised training of diffusion models as a synaptic learning process that encodes the associative dynamics of a modern Hopfield network in the weight structure of a deep neural network. Accordingly, in our experiments we show that the storage capacity of a continuous modern Hopfield network is identical to the capacity of a diffusion model. Our results establish a strong link between generative modeling and the theoretical neuroscience of memory, which provide a powerful computational foundation for the reconstructive theory of memory, where creative generation and memory recall can be seen as parts of a unified continuum.
Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides the generative dynamics into two distinct phases: 1) A linear steady-state dynamics around a central fixed-point and 2) an attractor dynamics directed towards the data manifold. These two "phases" are separated by the change in stability of the central fixed-point, with the resulting window of instability being responsible for the diversity of the generated samples. Using both theoretical and empirical evidence, we show that an accurate simulation of the early dynamics does not significantly contribute to the final generation, since early fluctuations are reverted to the central fixed point. To leverage this insight, we propose a Gaussian late initialization scheme, which significantly improves model performance, achieving up to 3x FID improvements on fast samplers, while also increasing sample diversity (e.g., racial composition of generated CelebA images). Our work offers a new way to understand the generative dynamics of diffusion models that has the potential to bring about higher performance and less biased fast-samplers.
In this work, we provide an exact likelihood alternative to the variational training of generative autoencoders. We show that VAE-style autoencoders can be constructed using invertible layers, which offer a tractable exact likelihood without the need for any regularization terms. This is achieved while leaving complete freedom in the choice of encoder, decoder and prior architectures, making our approach a drop-in replacement for the training of existing VAEs and VAE-style models. We refer to the resulting models as Autoencoders within Flows (AEF), since the encoder, decoder and prior are defined as individual layers of an overall invertible architecture. We show that the approach results in strikingly higher performance than architecturally equivalent VAEs in term of log-likelihood, sample quality and denoising performance. In a broad sense, the main ambition of this work is to close the gap between the normalizing flow and autoencoder literature under the common framework of invertibility and exact maximum likelihood.
Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normalizing flows cannot readily incorporate. We propose embedded-model flows (EMF), which alternate general-purpose transformations with structured layers that embed domain-specific inductive biases. These layers are automatically constructed by converting user-specified differentiable probabilistic models into equivalent bijective transformations. We also introduce gated structured layers, which allow bypassing the parts of the models that fail to capture the statistics of the data. We demonstrate that EMFs can be used to induce desirable properties such as multimodality, hierarchical coupling and continuity. Furthermore, we show that EMFs enable a high performance form of variational inference where the structure of the prior model is embedded in the variational architecture. In our experiments, we show that this approach outperforms state-of-the-art methods in common structured inference problems.
There is a strong link between the general concept of intelligence and the ability to collect and use information. The theory of Bayes-adaptive exploration offers an attractive optimality framework for training machines to perform complex information gathering tasks. However, the computational complexity of the resulting optimal control problem has limited the diffusion of the theory to mainstream deep AI research. In this paper we exploit the inherent mathematical structure of Bayes-adaptive problems in order to dramatically simplify the problem by making the reward structure denser while simultaneously decoupling the learning of exploitation and exploration policies. The key to this simplification comes from the novel concept of cross-value (i.e. the value of being in an environment while acting optimally according to another), which we use to quantify the value of currently available information. This results in a new denser reward structure that "cashes in" all future rewards that can be predicted from the current information state. In a set of experiments we show that the approach makes it possible to learn challenging information gathering tasks without the use of shaping and heuristic bonuses in situations where the standard RL algorithms fail.
Backpropagation of error (BP) is a widely used and highly successful learning algorithm. However, its reliance on non-local information in propagating error gradients makes it seem an unlikely candidate for learning in the brain. In the last decade, a number of investigations have been carried out focused upon determining whether alternative more biologically plausible computations can be used to approximate BP. This work builds on such a local learning algorithm - Gradient Adjusted Incremental Target Propagation (GAIT-prop) - which has recently been shown to approximate BP in a manner which appears biologically plausible. This method constructs local, layer-wise weight update targets in order to enable plausible credit assignment. However, in deep networks, the local weight updates computed by GAIT-prop can deviate from BP for a number of reasons. Here, we provide and test methods to overcome such sources of error. In particular, we adaptively rescale the locally-computed errors and show that this significantly increases the performance and stability of the GAIT-prop algorithm when applied to the CIFAR-10 dataset.
The automation of probabilistic reasoning is one of the primary aims of machine learning. Recently, the confluence of variational inference and deep learning has led to powerful and flexible automatic inference methods that can be trained by stochastic gradient descent. In particular, normalizing flows are highly parameterized deep models that can fit arbitrarily complex posterior densities. However, normalizing flows struggle in highly structured probabilistic programs as they need to relearn the forward-pass of the program. Automatic structured variational inference (ASVI) remedies this problem by constructing variational programs that embed the forward-pass. Here, we combine the flexibility of normalizing flows and the prior-embedding property of ASVI in a new family of variational programs, which we named cascading flows. A cascading flows program interposes a newly designed highway flow architecture in between the conditional distributions of the prior program such as to steer it toward the observed data. These programs can be constructed automatically from an input probabilistic program and can also be amortized automatically. We evaluate the performance of the new variational programs in a series of structured inference problems. We find that cascading flows have much higher performance than both normalizing flows and ASVI in a large set of structured inference problems.