Our main technical contribution is the rigorous analysis of a Bayes estimator and of an approximate message passing (AMP) algorithm, both of which incorrectly assume a Gaussian setup.

We study a spiked Wigner problem with an inhomogeneous noise profile.

Our main technical contribution is the rigorous analysis of a Bayes estimator and of an approximate message passing (AMP) algorithm, both of which incorrectly assume a Gaussian setup.

We label the phase in which we are at a given stage by colouring the circle below every plot.

We identify the information-theoretic threshold below which obtaining a positive correlation with the true cluster means is statistically impossible.

Scaling up model sizes can lead to fundamentally new capabilities in many machine learning (ML) tasks. However, training big models requires strong distributed system expertise to carefully design model-parallel execution strategies that suit the model architectures and cluster setups. In this paper, we develop AMP, a framework that automatically derives such strategies. AMP identifies a valid space of model parallelism strategies and efficiently searches the space for high-performed strategies, by leveraging a cost model designed to capture the heterogeneity of the model and cluster specifications. Unlike existing methods, AMP is specifically tailored to support complex models composed of uneven layers and cluster setups with more heterogeneous accelerators and bandwidth.

Hessian Center for Artificial Intelligence (Hessian.ai), This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings. Learning skills through imitation is probably the most cardinal form of learning for human beings. Whether it is a child learning to tie their shoelaces, a dancer learning a new pose, or a gymnast learning a fast and complex manoeuvre, acquiring new motor skills for humans typically involves guidance from another skilled human in the form of demonstrations. Acquiring skills from these demonstrations typically boils down to interpreting the individual features of the demonstration motion - for example, the relative positions of the limbs in a dance pose - and subsequently attempting to recreate the same features via repeated trial and error. Imitation learning (IL) is an algorithmic interpretation of this simple strategy of learning skills by matching the features of one's own motions with the features of the expert's demonstrations. Such a problem can be solved by various means, with techniques like behavioural cloning (BC), inverse reinforcement learning (IRL), and their variants being popular choices (Osa et al., 2018). The imitation learning problem can also be formulated in various subtly differing ways, leading to different constraints on the types of algorithms that solve the problem.

Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis. Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance. Here, the authors propose HydrAMP, an extended conditional variational autoencoder. HydrAMP generated antimicrobial peptides with high activity against bacteria, including multidrug-resistant species.

AMP Robotics Corp. ("AMP"), a pioneer in artificial intelligence (AI), robotics, and infrastructure for the waste and recycling industry, has raised $91 million in corporate equity in a Series C financing, led by Congruent Ventures and Wellington Management as well as new and existing investors including Blue Earth Capital, Sidewalk Infrastructure Partners (SIP), Tao Capital Partners, XN, Sequoia Capital, GV, Range Ventures, and Valor Equity Partners. This new round of funding follows a $55 million Series B financing led by XN in January 2021. "Our focus from the outset has been our application of AI-powered automation to economically and sustainably improve our global recycling system" "Advancements in robotics and automation are accelerating the transformation of traditional infrastructure, and AMP is seeking to reshape the waste and recycling industries," said Michael DeLucia, sector lead for Climate Investing, Wellington Management. "By bringing digital intelligence to the recycling industry, AMP can sort waste streams and extract additional value beyond what is otherwise possible." AMP will use the latest funding to scale its business operations while continuing its international expansion.